← All research areas

AI Security, Privacy & Forensics

Investigating how intelligent systems expose information, fail under attack, and leave evidence that can be examined.

Conceptual illustration of ai security, privacy & forensics

Research Description

Overview

We investigate how intelligent systems expose sensitive information, respond to adversarial manipulation and leave recoverable digital evidence. The scope spans text, audio, images, video and sensing data across consumer platforms, connected devices, LLMs and VLMs.

Projects examine privacy in writing and audio tools, wearable-data integrity, image-edit provenance and AI application artifacts. Published and preprint studies provide concrete foundations; broader cross-modal and video evaluation remain part of the evolving research agenda.

Research Thrusts

Adversarial integrity across modalities

Characterize manipulation of text, audio, images, video and sensing inputs, with published foundations in wearable pipelines and vision–language model evaluation. Broader cross-modal coverage is an ongoing research agenda.

Privacy in consumer AI and devices

Study information exposure in LLM/VLM-assisted platforms and connected devices, relating system behavior to user privacy and threat assumptions.

Forensic evidence and provenance

Examine image-edit traces and application artifacts to understand what evidence can be recovered and which attribution claims it can support.

Research Goals

Evaluate threats to learning systems and consumer AI while developing reproducible methods for privacy and forensic analysis.

Intellectual Merit

Connect model behavior, user-facing tools and recoverable digital evidence rather than treating these as isolated problems.

Research Impact

This work informs the evaluation of trustworthy consumer AI, sensing systems and digital evidence. Its value lies in reproducible threat analysis and explicit limits on what a detector or forensic method can establish.

Across Modalities, Platforms and Devices

Our security, privacy and forensic research considers text, audio, images, video and sensing data across consumer platforms and connected devices, including large language models (LLMs) and vision–language models (VLMs). The central questions are what information can leak, how evidence can be manipulated, how model behavior changes, and what traces remain available for examination.

Published and preprint foundations include consumer writing and audio tools, image-edit provenance, wearable-data integrity, VLM robustness and AI application artifacts. Broader video and cross-device evaluation form part of the research agenda rather than a claim of completed coverage across every modality.

Text & audioImages & videoSensing dataLLMs & VLMsConsumer platforms & devices

Current Projects & Emerging Directions

Existing research

Wearable AI across the lifecycle

Sensor dataIntegrity checksReliable interpretation

Wearable learning pipelines turn time-varying measurements into activity and wellbeing inferences. Changes to training signals, labels or cross-modal alignment can affect both predictive behavior and the trustworthiness of subsequent explanations.

Research objectives

Study data integrity, poisoning detection and sanitization while evaluating whether useful activity information is retained.

Approach & Intellectual Merit

Existing studies examine wearable activity recognition, poisoning and privacy-aware distributed learning. The LLM-based detection work is a preprint; detection, localization and recovery must be evaluated separately rather than treated as interchangeable successes.

Selected publications

Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models ↗

Relevance & Applications

The work supports research on dependable sensing pipelines in healthcare, wellbeing and connected environments. Benchmark performance does not by itself establish clinical effectiveness or safety.

Impact

The linked research investigates poisoning detection and sanitization in wearable IoT data. The potential benefit is more trustworthy sensing pipelines; clinical effectiveness, patient benefit, and production deployment have not been established here.

Existing research

Privacy in human–AI interaction

Text / audioConsumer AI transformationPrivacy ↔ utility

Everyday writing and audio-editing tools may reveal sensitive attributes, but may also help transform content to reduce unwanted inference. The same consumer interface can therefore act as both a privacy risk and a possible defense.

Research objectives

Measure how transformations affect sensitive-attribute inference while preserving the usefulness and meaning of the original content.

Approach & Intellectual Merit

Published writing-assistant and audio-editing studies motivate controlled comparisons across original and transformed inputs. Privacy protection, task utility and model-specific behavior must be assessed together; fluent rewrites alone do not demonstrate protection.

Selected publications

No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants ↗

Relevance & Applications

Relevant settings include consumer platforms, communication tools and device-integrated assistants using LLMs. Results support informed evaluation of privacy tradeoffs, not universal guarantees across people, models or platforms.

Impact

The published work examines both privacy-protection capabilities and security risks. It may help researchers and users assess tradeoffs, but does not establish universal privacy guarantees or measured adoption outcomes.

EMNLP 2026

On-device generative image-edit forensics

Consumer image editDetect & localizeProvenance evidence

Consumer editing tools can alter a localized part of an image while leaving most of the scene intact. Detecting these changes requires attention to real device workflows, not only to images generated entirely from scratch.

Research objectives

Detect and localize consumer-tool edits, evaluate multilingual edit descriptions and examine the effects of compression.

Approach & Intellectual Merit

The published Edits in the Wild work introduces ConsumerGenEdit as a benchmark grounded in consumer platforms. Its intellectual contribution is an evaluation setting that links localized edits, platform conditions and language-based descriptions.

Selected publications

Edits in the Wild: A Multilingual Benchmark for Localizing On-Device Generative Image Edits on Consumer Platforms ↗

Relevance & Applications

The benchmark is relevant to provenance research and potential fact-checking workflows. An edit localization is evidence about a modification, not proof of malicious intent or a complete history of the image.

Impact

The benchmark supports evaluation of edit detection and localization in realistic consumer workflows. Its potential benefit is stronger image-provenance assessment; forensic outputs alone do not prove an image’s truth, intent, or complete editing history.

Preprint

AI application forensics

Application activityRecoverable artifactsQualified interpretation

AI applications leave digital traces beyond their visible conversations. Understanding which artifacts persist, and what they can legitimately establish, is important for reproducible examination of emerging interfaces.

Research objectives

Identify and characterize traces associated with the ChatGPT Windows application and their interpretation in forensic research.

Approach & Intellectual Merit

The linked preprint studies application artifacts. A sound approach distinguishes an observed trace from an inferred user action, records application conditions, and considers how versions or settings may change artifact availability.

Selected publications

Digital Forensic Investigation of the ChatGPT Windows Application ↗

Relevance & Applications

Potential use lies in authorized forensic examination and research. Any operational use requires lawful access, independent validation and appropriate evidence-handling procedures.

Impact

The linked preprint characterizes application traces that may support evidence analysis. Any operational use requires independent validation, lawful access, and appropriate evidence-handling procedures; investigative or legal outcomes are not claimed.

Related Publications

CVPR WorkshopWorkshop

Breaking Sensor-Text Alignment: Cross-Modal Attack on Contrastive Multimodal Human Activity Recognition

Malithi Mithsara Wanniarachchi Kankanamge, Ning Yang, Ahmed Imteaj, Abdur R. Shahid

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops · pp. 3966-3975, 2026

AI Security & PrivacyMultimodal AIWearable Sensing
PDFPaper ↗
BibTeX
@inproceedings{shield73,
  title = {Breaking Sensor-Text Alignment: Cross-Modal Attack on Contrastive Multimodal Human Activity Recognition},
  author = {Malithi Mithsara Wanniarachchi Kankanamge and Ning Yang and Ahmed Imteaj and Abdur R. Shahid},
  year = {2026},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
  pages = {3966-3975},
  url = {https://openaccess.thecvf.com/content/CVPR2026W/SenseOfSpace/html/Kankanamge_Breaking_Sensor-Text_Alignment_Cross-Modal_Attack_on_Contrastive_Multimodal_Human_Activity_CVPRW_2026_paper.html}
}
ICORE A*2026 editionConference

Edits in the Wild: A Multilingual Benchmark for Localizing On-Device Generative Image Edits on Consumer Platforms

Mohd. Farhan Israk Soumik, Awal Ahmed Fime, Malithi Mithsara Wanniarachchi Kankanamge, Arun Babu Aryal, Hoda Joudi Haghighi, Bibek Koirala, Ahmed Imteaj, Abdur R. Shahid

Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing · pp. 37756–37789, 2026

Digital ForensicsComputer VisionMultimodal AI
Paper ↗
BibTeX
@inproceedings{shield86,
  title = {Edits in the Wild: A Multilingual Benchmark for Localizing On-Device Generative Image Edits on Consumer Platforms},
  author = {Mohd. Farhan Israk Soumik and Awal Ahmed Fime and Malithi Mithsara Wanniarachchi Kankanamge and Arun Babu Aryal and Hoda Joudi Haghighi and Bibek Koirala and Ahmed Imteaj and Abdur R. Shahid},
  year = {2026},
  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
  pages = {37756–37789},
  url = {https://aclanthology.org/2026.emnlp-main.1661/}
}
Preprint

Emotion-Aware Clickbait Attack in Social Media

Syed Mhamudul Hasan, Mohd Soumik, Abdur R Shahid

arXiv preprint arXiv:2604.27369 · 2026

AI Security & Privacy
PDFPaper ↗
BibTeX
@misc{shield76,
  title = {Emotion-Aware Clickbait Attack in Social Media},
  author = {Syed Mhamudul Hasan and Mohd Soumik and Abdur R Shahid},
  year = {2026},
  howpublished = {arXiv preprint arXiv:2604.27369},
  url = {https://arxiv.org/abs/2604.27369}
}
Preprint

Evaluating Federated Vision-Language and Vision-Only Models for Privacy-Aware Breast Cancer Imaging

Malithi Mithsara Wanniarachchi Kankanamge, Ning Yang, Sree Bash Debnath, Md Zobaer Islam, Abdur R Shahid

arXiv preprint arXiv:2610.36379 · 2026

Federated LearningHealthcare AIMultimodal AI
PDFPaper ↗
BibTeX
@misc{shield88,
  title = {Evaluating Federated Vision-Language and Vision-Only Models for Privacy-Aware Breast Cancer Imaging},
  author = {Malithi Mithsara Wanniarachchi Kankanamge and Ning Yang and Sree Bash Debnath and Md Zobaer Islam and Abdur R Shahid},
  year = {2026},
  howpublished = {arXiv preprint arXiv:2610.36379},
  url = {https://arxiv.org/abs/2610.36379}
}
Conference

No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants

Mohd. Farhan Israk Soumik, Syed Mhamudul Hasan, Wanniarachchi Kankanamge Malithi Mithsara, Ahmed Imteaj, Abdur R. Shahid

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · pp. 1866–1885, 2026

AI Security & PrivacyLLMs
PDFPaper ↗DOI ↗
BibTeX
@inproceedings{shield75,
  title = {No Innocence in Styling: Discovery of Privacy Protection Capabilities and Security Risks in Consumer Generative AI Writing Assistants},
  author = {Mohd. Farhan Israk Soumik and Syed Mhamudul Hasan and Wanniarachchi Kankanamge Malithi Mithsara and Ahmed Imteaj and Abdur R. Shahid},
  year = {2026},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)},
  pages = {1866–1885},
  publisher = {Association for Computational Linguistics},
  doi = {10.18653/v1/2026.acl-industry.128},
  url = {https://aclanthology.org/2026.acl-industry.128/}
}
JIF 5.32025 metricJournal

Quantifying Robustness and Sustainability Trade-off in Federated Adversarial Learning for Cyber-Physical Systems

Syed Mhamudul Hasan, Ahmed Imteaj, Abdur R Shahid

IEEE Transactions on Sustainable Computing · 2026

AI Security & PrivacyFederated LearningSustainable & Resource-Efficient AI
Paper ↗DOI ↗
BibTeX
@article{shield70,
  title = {Quantifying Robustness and Sustainability Trade-off in Federated Adversarial Learning for Cyber-Physical Systems},
  author = {Syed Mhamudul Hasan and Ahmed Imteaj and Abdur R Shahid},
  year = {2026},
  journal = {IEEE Transactions on Sustainable Computing},
  publisher = {IEEE},
  doi = {10.1109/TSUSC.2025.3633995},
  url = {https://doi.org/10.1109/TSUSC.2025.3633995}
}
JIF 4.92025 metricJournal

Secure Yet Fragile: Adversarial Vulnerabilities of Federated Vision–Language Models in Medical AI

A.A. Fime, T.Z. Samiha, M.Z. Hossain, S. Zaman, A.M. Shibli, A.R. Shahid, Zhen Ni, A. Imteaj

Nature Scientific Reports Journal · 2026

AI Security & PrivacyFederated LearningMultimodal AI
Paper ↗DOI ↗
BibTeX
@article{shield72,
  title = {Secure Yet Fragile: Adversarial Vulnerabilities of Federated Vision–Language Models in Medical AI},
  author = {A.A. Fime and T.Z. Samiha and M.Z. Hossain and S. Zaman and A.M. Shibli and A.R. Shahid and Zhen Ni and A. Imteaj},
  year = {2026},
  journal = {Nature Scientific Reports Journal},
  publisher = {Nature},
  doi = {10.1038/s41598-026-48102-4},
  url = {https://doi.org/10.1038/s41598-026-48102-4}
}
Preprint

Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models

W. K. M Mithsara, Ning Yang, Ahmed Imteaj, Hussein Zangoti, Abdur R. Shahid

arXiv · 2025

AI Security & PrivacyLLMsWearable Sensing
PDFPaper ↗
BibTeX
@misc{shield69,
  title = {Adaptive and Robust Data Poisoning Detection and Sanitization in Wearable IoT Systems using Large Language Models},
  author = {W. K. M Mithsara and Ning Yang and Ahmed Imteaj and Hussein Zangoti and Abdur R. Shahid},
  year = {2025},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2511.02894}
}
Workshop

Audio Editing Features As User-Centric Privacy Defenses Against Large Language Model (LLM)-Based Emotion Inference Attacks

Mohd. Farhan Israk Soumik, W.K.M Mithsara, Abdur Rahman Bin Shahid, Ahmed Imteaj

The Sixth AAAI-25 Workshop on Privacy-Preserving Artificial Intelligence · 2025

AI Security & PrivacyLLMs
PDFPaper ↗
BibTeX
@inproceedings{shield55,
  title = {Audio Editing Features As User-Centric Privacy Defenses Against Large Language Model (LLM)-Based Emotion Inference Attacks},
  author = {Mohd. Farhan Israk Soumik and W.K.M Mithsara and Abdur Rahman Bin Shahid and Ahmed Imteaj},
  year = {2025},
  booktitle = {The Sixth AAAI-25 Workshop on Privacy-Preserving Artificial Intelligence},
  publisher = {https://arxiv.org/abs/2501.18727},
  url = {https://arxiv.org/abs/2501.18727}
}
Conference

Breaking and Securing Vision-Language Models: An Adversarial Robustness Study

Md Zarif Hossain, Abdur R Shahid, Ahmed Imteaj

2025 International Conference on Machine Learning and Applications (ICMLA) · pp. 1411-1416, 2025

AI Security & PrivacyMultimodal AI
Paper ↗DOI ↗
BibTeX
@inproceedings{shield71,
  title = {Breaking and Securing Vision-Language Models: An Adversarial Robustness Study},
  author = {Md Zarif Hossain and Abdur R Shahid and Ahmed Imteaj},
  year = {2025},
  booktitle = {2025 International Conference on Machine Learning and Applications (ICMLA)},
  pages = {1411-1416},
  publisher = {IEEE},
  doi = {10.1109/ICMLA66185.2025.00215},
  url = {https://doi.org/10.1109/ICMLA66185.2025.00215}
}
Preprint

Digital Forensic Investigation of the ChatGPT Windows Application

Malithi Wanniarachchi Kankanamge, Nick McKenna, Santiago Carmona, Syed Mhamudul Hasan, Abdur R. Shahid, Ahmed Imteaj

arXiv · 2025

Digital Forensics
PDFPaper ↗
BibTeX
@misc{shield60,
  title = {Digital Forensic Investigation of the ChatGPT Windows Application},
  author = {Malithi Wanniarachchi Kankanamge and Nick McKenna and Santiago Carmona and Syed Mhamudul Hasan and Abdur R. Shahid and Ahmed Imteaj},
  year = {2025},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2505.23938}
}
Preprint

Evaluating Apple Intelligence's Writing Tools for Privacy Against Large Language Model-Based Inference Attacks: Insights from Early Datasets

Mohd. Farhan Israk Soumik, Syed Mhamudul Hasan, Abdur R. Shahid

arXiv preprint arXiv:2506.03870 · 2025

AI Security & PrivacyLLMs
PDFPaper ↗DOI ↗
BibTeX
@misc{shield62,
  title = {Evaluating Apple Intelligence's Writing Tools for Privacy Against Large Language Model-Based Inference Attacks: Insights from Early Datasets},
  author = {Mohd. Farhan Israk Soumik and Syed Mhamudul Hasan and Abdur R. Shahid},
  year = {2025},
  howpublished = {arXiv preprint arXiv:2506.03870},
  doi = {10.48550/arXiv.2506.03870},
  url = {https://arxiv.org/abs/2506.03870}
}
JIF 5.02025 metricJournal

Evaluating sustainability and social costs of adversarial training in machine learning

Syed Mhamudul Hasan, Abdur R. Shahid, Ahmed Imteaj

IEEE Consumer Electronics Magazine · vol. 14, no. 3, pp. 27-34, 2025

AI Security & PrivacySustainable & Resource-Efficient AI
Paper ↗DOI ↗
BibTeX
@article{shield51,
  title = {Evaluating sustainability and social costs of adversarial training in machine learning},
  author = {Syed Mhamudul Hasan and Abdur R. Shahid and Ahmed Imteaj},
  year = {2025},
  journal = {IEEE Consumer Electronics Magazine},
  volume = {14},
  number = {3},
  pages = {27-34},
  publisher = {IEEE},
  doi = {10.1109/MCE.2024.3458350},
  url = {https://doi.org/10.1109/MCE.2024.3458350}
}
Conference

Privacy-Preserving Multimodal Stress Detection from Wearables with Attention Fusion and Federated Learning

Mohd Farhan Israk Soumik, Hussein Zangoti, Ebrahim Maghsoudlou, Awal Ahmed Fime, Ahmed Imteaj, Abdur R Shahid

2025 International Conference on Machine Learning and Applications (ICMLA) · pp. 1369-1375, 2025

AI Security & PrivacyFederated LearningWearable Sensing
Paper ↗DOI ↗
BibTeX
@inproceedings{shield74,
  title = {Privacy-Preserving Multimodal Stress Detection from Wearables with Attention Fusion and Federated Learning},
  author = {Mohd Farhan Israk Soumik and Hussein Zangoti and Ebrahim Maghsoudlou and Awal Ahmed Fime and Ahmed Imteaj and Abdur R Shahid},
  year = {2025},
  booktitle = {2025 International Conference on Machine Learning and Applications (ICMLA)},
  pages = {1369-1375},
  publisher = {IEEE},
  doi = {10.1109/ICMLA66185.2025.00209},
  url = {https://doi.org/10.1109/ICMLA66185.2025.00209}
}
IEEE GLOBECOMConference

Sponge attacks on sensing ai: Energy-latency vulnerabilities and defense via model pruning

Syed Mhamudul Hasan, Hussein Zangoti, Iraklis Anagnostopoulos, Abdur R. Shahid

GLOBECOM 2025-2025 IEEE Global Communications Conference · pp. 4445-4450, 2025

AI Security & PrivacySustainable & Resource-Efficient AIWearable Sensing
Paper ↗DOI ↗
BibTeX
@inproceedings{shield57,
  title = {Sponge attacks on sensing ai: Energy-latency vulnerabilities and defense via model pruning},
  author = {Syed Mhamudul Hasan and Hussein Zangoti and Iraklis Anagnostopoulos and Abdur R. Shahid},
  year = {2025},
  booktitle = {GLOBECOM 2025-2025 IEEE Global Communications Conference},
  pages = {4445-4450},
  publisher = {IEEE},
  doi = {10.1109/GLOBECOM59602.2025.11432163},
  url = {https://doi.org/10.1109/GLOBECOM59602.2025.11432163}
}
CVPR WorkshopWorkshop

Towards trustworthy autonomous vehicles with vision-language models under targeted and untargeted adversarial attacks

Awal Ahmed Fime, Md Zarif Hossain, Saika Zaman, Abdur R Shahid, Ahmed Imteaj

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · pp. 619-628, 2025

AI Security & PrivacyMultimodal AIComputer Vision
Paper ↗
BibTeX
@inproceedings{shield63,
  title = {Towards trustworthy autonomous vehicles with vision-language models under targeted and untargeted adversarial attacks},
  author = {Awal Ahmed Fime and Md Zarif Hossain and Saika Zaman and Abdur R Shahid and Ahmed Imteaj},
  year = {2025},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  pages = {619-628},
  publisher = {IEEE},
  url = {https://openaccess.thecvf.com/content/CVPR2025W/TCV/html/Fime_Towards_Trustworthy_Autonomous_Vehicles_with_Vision-Language_Models_Under_Targeted_and_CVPRW_2025_paper.html}
}
INFOCOM PosterWorkshop

Context-Aware Spatiotemporal Poisoning Attacks on Wearable-Based Activity Recognition

Abdur R. Shahid, Syed Mhamudul Hasan, Ahmed Imteaj, Shahriar Badsha

IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · 2024

AI Security & PrivacyWearable Sensing
Paper ↗DOI ↗
BibTeX
@inproceedings{shield36,
  title = {Context-Aware Spatiotemporal Poisoning Attacks on Wearable-Based Activity Recognition},
  author = {Abdur R. Shahid and Syed Mhamudul Hasan and Ahmed Imteaj and Shahriar Badsha},
  year = {2024},
  booktitle = {IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)},
  doi = {10.1109/infocomwkshps61880.2024.10620768},
  url = {https://doi.org/10.1109/infocomwkshps61880.2024.10620768}
}
Conference Poster

Detection of Poisoning Attacks in Human Activity Recognition using Large Language Models

W.K.M Mithsara, Abdur R. Shahid, Ning Yang

IEEE-EMBS International Conference on Body Sensor Networks (IEEE BSN) · 2024

AI Security & PrivacyLLMsWearable Sensing
Conference program ↗
BibTeX
@misc{shield49,
  title = {Detection of Poisoning Attacks in Human Activity Recognition using Large Language Models},
  author = {W.K.M Mithsara and Abdur R. Shahid and Ning Yang},
  year = {2024},
  howpublished = {IEEE-EMBS International Conference on Body Sensor Networks (IEEE BSN)}
}
Conference

Distributed threat intelligence at the edge devices: A large language model-driven approach

Syed Mhamudul Hasan, Alaa M Alotaibi, Sajedul Talukder, Abdur R Shahid

2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC) · pp. 1496-1497, 2024

AI Security & PrivacyLLMs
Paper ↗DOI ↗
BibTeX
@inproceedings{shield40,
  title = {Distributed threat intelligence at the edge devices: A large language model-driven approach},
  author = {Syed Mhamudul Hasan and Alaa M Alotaibi and Sajedul Talukder and Abdur R Shahid},
  year = {2024},
  booktitle = {2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC)},
  pages = {1496-1497},
  publisher = {IEEE},
  doi = {10.1109/compsac61105.2024.00206},
  url = {https://doi.org/10.1109/compsac61105.2024.00206}
}
Workshop

FLAMINGO: Adaptive and Resilient Federated Meta-Learning against Adversarial Attacks

Md Zarif Hossain, Ahmed Imteaj, Abdur R. Shahid

2024 IEEE 44th International Conference on Distributed Computing Systems Workshops (ICDCSW) · 2024

AI Security & PrivacyFederated Learning
PDFPaper ↗DOI ↗
BibTeX
@inproceedings{shield42,
  title = {FLAMINGO: Adaptive and Resilient Federated Meta-Learning against Adversarial Attacks},
  author = {Md Zarif Hossain and Ahmed Imteaj and Abdur R. Shahid},
  year = {2024},
  booktitle = {2024 IEEE 44th International Conference on Distributed Computing Systems Workshops (ICDCSW)},
  doi = {10.1109/icdcsw63686.2024.00009},
  url = {https://doi.org/10.1109/ICDCSW63686.2024.00009}
}
NeurIPS Workshop · PosterPoster / abstract

Poster: Leveraging Large Language Models for Zero-Shot Detection and Mitigation of Data Poisoning in Wearable AI Systems

Malithi Wanniarachchi Kankanamge, Abdur R Shahid, Ning Yang

NeurIPS workshop on GenAI for Health: Potential, Trust and Policy Compliance · 2024

AI Security & PrivacyLLMsWearable Sensing
PDFPaper ↗
BibTeX
@misc{shield54,
  title = {Poster: Leveraging Large Language Models for Zero-Shot Detection and Mitigation of Data Poisoning in Wearable AI Systems},
  author = {Malithi Wanniarachchi Kankanamge and Abdur R Shahid and Ning Yang},
  year = {2024},
  howpublished = {NeurIPS workshop on GenAI for Health: Potential, Trust and Policy Compliance},
  url = {https://openreview.net/forum?id=GAEZOAqrtA}
}
Journal

Securing Privacy in Cloud-Based Whiteboard Services Against Health Attribute Inference Attacks

Abdur R. Shahid, Ahmed Imteaj

IEEE Transactions on Artificial Intelligence · pp. 1-13, 2024

AI Security & Privacy
Paper ↗DOI ↗
BibTeX
@article{shield30,
  title = {Securing Privacy in Cloud-Based Whiteboard Services Against Health Attribute Inference Attacks},
  author = {Abdur R. Shahid and Ahmed Imteaj},
  year = {2024},
  journal = {IEEE Transactions on Artificial Intelligence},
  pages = {1-13},
  publisher = {IEEE},
  doi = {10.1109/tai.2024.3352529},
  url = {https://doi.org/10.1109/tai.2024.3352529}
}
JIF 6.12025 metricJournal

Sticks and Stones May Break My Bones, But Words Will Never Hurt Me! — Navigating the Cybersecurity Risks of Generative AI

Abdur R. Shahid, Ahmed Imteaj

AI & Society · 2024

AI Security & PrivacyLLMs
Paper ↗DOI ↗
BibTeX
@article{shield38,
  title = {Sticks and Stones May Break My Bones, But Words Will Never Hurt Me! — Navigating the Cybersecurity Risks of Generative AI},
  author = {Abdur R. Shahid and Ahmed Imteaj},
  year = {2024},
  journal = {AI & Society},
  publisher = {Springer},
  doi = {10.1007/s00146-024-01934-y},
  url = {https://doi.org/10.1007/s00146-024-01934-y}
}
IEEE ICC WorkshopWorkshop

Towards sustainable secureml: Quantifying carbon footprint of adversarial machine learning

Syed Mhamudul Hasan, Abdur R. Shahid, Ahmed Imteaj

2024 IEEE International Conference on Communications Workshops (ICC Workshops) · pp. 1359-1364, 2024

AI Security & PrivacySustainable & Resource-Efficient AI
Paper ↗DOI ↗
BibTeX
@inproceedings{shield39,
  title = {Towards sustainable secureml: Quantifying carbon footprint of adversarial machine learning},
  author = {Syed Mhamudul Hasan and Abdur R. Shahid and Ahmed Imteaj},
  year = {2024},
  booktitle = {2024 IEEE International Conference on Communications Workshops (ICC Workshops)},
  pages = {1359-1364},
  publisher = {IEEE},
  doi = {10.1109/ICCWorkshops59551.2024.10615723},
  url = {https://doi.org/10.1109/ICCWorkshops59551.2024.10615723}
}
Conference

Zero-Shot Detection and Sanitization of Data Poisoning Attacks in Wearable AI using Large Language Models

W.K.M Mithsara, Abdur R. Shahid, Ning Yang

2024 International Conference on Machine Learning and Applications (ICMLA) · 2024

AI Security & PrivacyLLMsWearable Sensing
Paper ↗DOI ↗
BibTeX
@inproceedings{shield53,
  title = {Zero-Shot Detection and Sanitization of Data Poisoning Attacks in Wearable AI using Large Language Models},
  author = {W.K.M Mithsara and Abdur R. Shahid and Ning Yang},
  year = {2024},
  booktitle = {2024 International Conference on Machine Learning and Applications (ICMLA)},
  doi = {10.1109/ICMLA61862.2024.00233},
  url = {https://doi.org/10.1109/ICMLA61862.2024.00233}
}
Conference

Assessing wearable human activity recognition systems against data poisoning attacks in differentially-private federated learning

Abdur R Shahid, Ahmed Imteaj, Shahriar Badsha, Md Zarif Hossain

2023 IEEE International Conference on Smart Computing (SMARTCOMP) · pp. 355-360, 2023

AI Security & PrivacyFederated LearningWearable Sensing
Paper ↗DOI ↗
BibTeX
@inproceedings{shield26,
  title = {Assessing wearable human activity recognition systems against data poisoning attacks in differentially-private federated learning},
  author = {Abdur R Shahid and Ahmed Imteaj and Shahriar Badsha and Md Zarif Hossain},
  year = {2023},
  booktitle = {2023 IEEE International Conference on Smart Computing (SMARTCOMP)},
  pages = {355-360},
  publisher = {IEEE},
  doi = {10.1109/smartcomp58114.2023.00085},
  url = {https://doi.org/10.1109/smartcomp58114.2023.00085}
}
Conference

FLID: Intrusion Attack and Defense Mechanism for Federated Learning-Empowered Connected Autonomous Vehicles

Md Zarif Hossain, Imteaj Ahmed, Saika Zaman, Abdur R Shahid, Sajedul Talukder, MH Amini

2023 6th IEEE Conference on Dependable and Secure Computing (IEEE DSC 2023) · 2023

AI Security & PrivacyFederated LearningCyber-Physical Systems & IoT
Paper ↗DOI ↗
BibTeX
@inproceedings{shield29,
  title = {FLID: Intrusion Attack and Defense Mechanism for Federated Learning-Empowered Connected Autonomous Vehicles},
  author = {Md Zarif Hossain and Imteaj Ahmed and Saika Zaman and Abdur R Shahid and Sajedul Talukder and MH Amini},
  year = {2023},
  booktitle = {2023 6th IEEE Conference on Dependable and Secure Computing (IEEE DSC 2023)},
  doi = {10.1109/dsc61021.2023.10354149},
  url = {https://doi.org/10.1109/dsc61021.2023.10354149}
}
Book chapter

Protecting Location Privacy in Blockchain-Based Mobile Internet of Things

Abdur R. Shahid, Niki Pissinou, Sajedul Talukder

Principles and Practice of Blockchains · pp. 93-118, 2023

AI Security & PrivacyBlockchainCyber-Physical Systems & IoT
Paper ↗DOI ↗
BibTeX
@incollection{shield22,
  title = {Protecting Location Privacy in Blockchain-Based Mobile Internet of Things},
  author = {Abdur R. Shahid and Niki Pissinou and Sajedul Talukder},
  year = {2023},
  booktitle = {Principles and Practice of Blockchains},
  pages = {93-118},
  publisher = {Springer International Publishing, Cham},
  doi = {10.1007/978-3-031-10507-4_5},
  url = {https://doi.org/10.1007/978-3-031-10507-4_5}
}
Conference

Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System

Abdur R. shahid, Ahmed Imteaj, Wu Peter Y., Igoche Diane A., Tauhidul Alam

IEEE Symposium Series on Computational Intelligence (SSCI) · pp. 908-914, 2022

AI Security & PrivacyWearable Sensing
Paper ↗DOI ↗
BibTeX
@inproceedings{shield25,
  title = {Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System},
  author = {Abdur R. shahid and Ahmed Imteaj and Wu Peter Y. and Igoche Diane A. and Tauhidul Alam},
  year = {2022},
  booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)},
  pages = {908-914},
  doi = {10.1109/ssci51031.2022.10022015},
  url = {https://doi.org/10.1109/ssci51031.2022.10022015}
}
Conference

A Study of Differentially Private Machine Learning in Healthcare

Abdur R. Shahid, Sajedul Talukder

2021 Innovations in Intelligent Systems and Applications Conference (ASYU) · 2021

AI Security & PrivacyHealthcare AI
Paper ↗DOI ↗
BibTeX
@inproceedings{shield16,
  title = {A Study of Differentially Private Machine Learning in Healthcare},
  author = {Abdur R. Shahid and Sajedul Talukder},
  year = {2021},
  booktitle = {2021 Innovations in Intelligent Systems and Applications Conference (ASYU)},
  doi = {10.1109/asyu52992.2021.9598991},
  url = {https://doi.org/10.1109/asyu52992.2021.9598991}
}
Poster / abstract

Applying local differential privacy in handwriting recognition-based systems: faculty poster abstract

Sajedul Talukder, Abdur R Shahid

Journal of Computing Sciences in Colleges · vol. 37, no. 3, pp. 163-163, 2021

AI Security & PrivacyComputer Vision
PDFPaper ↗
BibTeX
@misc{shield20,
  title = {Applying local differential privacy in handwriting recognition-based systems: faculty poster abstract},
  author = {Sajedul Talukder and Abdur R Shahid},
  year = {2021},
  howpublished = {Journal of Computing Sciences in Colleges},
  volume = {37},
  number = {3},
  pages = {163-163},
  publisher = {Consortium for Computing Sciences in Colleges},
  url = {https://www.ccsc.org/publications/journals/EA2021.pdf#page=165}
}
Conference

Evaluating Machine Learning Models for Handwriting Recognition-based Systems under Local Differential Privacy

Abdur R. Shahid, Sajedul Talukder

2021 Innovations in Intelligent Systems and Applications Conference (ASYU) · 2021

AI Security & PrivacyComputer Vision
Paper ↗DOI ↗
BibTeX
@inproceedings{shield15,
  title = {Evaluating Machine Learning Models for Handwriting Recognition-based Systems under Local Differential Privacy},
  author = {Abdur R. Shahid and Sajedul Talukder},
  year = {2021},
  booktitle = {2021 Innovations in Intelligent Systems and Applications Conference (ASYU)},
  doi = {10.1109/asyu52992.2021.9598983},
  url = {https://doi.org/10.1109/asyu52992.2021.9598983}
}
Poster / abstract

Evaluation of privacy-preserving Logistic Regression and Naive Bayes classifiers in healthcare: faculty poster abstract

Abdur R Shahid, Sajedul Talukder

Journal of Computing Sciences in Colleges · vol. 37, no. 3, pp. 164-164, 2021

AI Security & PrivacyHealthcare AI
PDFPaper ↗
BibTeX
@misc{shield19,
  title = {Evaluation of privacy-preserving Logistic Regression and Naive Bayes classifiers in healthcare: faculty poster abstract},
  author = {Abdur R Shahid and Sajedul Talukder},
  year = {2021},
  howpublished = {Journal of Computing Sciences in Colleges},
  volume = {37},
  number = {3},
  pages = {164-164},
  publisher = {Consortium for Computing Sciences in Colleges},
  url = {https://www.ccsc.org/publications/journals/EA2021.pdf#page=166}
}
Poster / abstract

Privacy-preserving activity recognition from sensor data: faculty poster abstract

Abdur R Shahid, Sajedul Talukder

Journal of Computing Sciences in Colleges · vol. 37, no. 3, pp. 165-165, 2021

AI Security & PrivacyWearable Sensing
PDFPaper ↗
BibTeX
@misc{shield18,
  title = {Privacy-preserving activity recognition from sensor data: faculty poster abstract},
  author = {Abdur R Shahid and Sajedul Talukder},
  year = {2021},
  howpublished = {Journal of Computing Sciences in Colleges},
  volume = {37},
  number = {3},
  pages = {165-165},
  publisher = {Consortium for Computing Sciences in Colleges},
  url = {https://www.ccsc.org/publications/journals/EA2021.pdf#page=167}
}
Conference

Block-Phasor: A Decentralized Blockchain Framework to Enhance Security of Synchrophasor

Arpan Bhattacharjee, Shahriar Badsha, Abdur R. Shahid, Hanif Livani, Shamik Sengupta

2020 Kansas Power and Energy Conference (KPEC) · 2020

AI Security & PrivacyBlockchainCyber-Physical Systems & IoT
Paper ↗DOI ↗
BibTeX
@inproceedings{shield10,
  title = {Block-Phasor: A Decentralized Blockchain Framework to Enhance Security of Synchrophasor},
  author = {Arpan Bhattacharjee and Shahriar Badsha and Abdur R. Shahid and Hanif Livani and Shamik Sengupta},
  year = {2020},
  booktitle = {2020 Kansas Power and Energy Conference (KPEC)},
  doi = {10.1109/kpec47870.2020.9167676},
  url = {https://doi.org/10.1109/kpec47870.2020.9167676}
}
Journal

Delay-Aware Privacy-Preserving Location-Based Services Under Spatiotemporal Constraints

Abdur R. Shahid, Niki Pissinou, S.S. Iyengar, Kia Makki

International Journal of Communication Systems · 2020

AI Security & Privacy
Paper ↗DOI ↗
BibTeX
@article{shield11,
  title = {Delay-Aware Privacy-Preserving Location-Based Services Under Spatiotemporal Constraints},
  author = {Abdur R. Shahid and Niki Pissinou and S.S. Iyengar and Kia Makki},
  year = {2020},
  journal = {International Journal of Communication Systems},
  publisher = {Wiley},
  doi = {10.1002/dac.4656},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/dac.4656}
}
Conference

Leveraging Blockchain for Spoof-Resilient Robot Networks

T Alam, J Talylor, S Badsha, A Shahid, A.S.M Kayes

International Conference on Intelligent Robotics and Applications · 2020

AI Security & PrivacyBlockchainCyber-Physical Systems & IoT
Paper ↗DOI ↗
BibTeX
@inproceedings{shield13,
  title = {Leveraging Blockchain for Spoof-Resilient Robot Networks},
  author = {T Alam and J Talylor and S Badsha and A Shahid and A.S.M Kayes},
  year = {2020},
  booktitle = {International Conference on Intelligent Robotics and Applications},
  doi = {10.1007/978-3-030-66645-3_18},
  url = {https://doi.org/10.1007/978-3-030-66645-3_18}
}
Preprint

$ n $-VDD: Location Privacy Protection Based on Voronoi-Delaunay Duality

Wei Zeng, Abdur B Shahid, Keyan Zolfaghari, Aditya Shetty, Niki Pissinou, Sitharama S Iyengar

arXiv preprint arXiv:1906.09158 · 2019

AI Security & Privacy
PDFPaper ↗DOI ↗
BibTeX
@misc{shield6,
  title = {$ n $-VDD: Location Privacy Protection Based on Voronoi-Delaunay Duality},
  author = {Wei Zeng and Abdur B Shahid and Keyan Zolfaghari and Aditya Shetty and Niki Pissinou and Sitharama S Iyengar},
  year = {2019},
  howpublished = {arXiv preprint arXiv:1906.09158},
  doi = {10.48550/arXiv.1906.09158},
  url = {https://arxiv.org/abs/1906.09158}
}
Conference

Quantifying location privacy in permissioned blockchain-based internet of things (IoT)

Abdur R. Shahid, Niki Pissinou, Laurent Njilla, Sheila Alemany, Ahmed Imteaj, Kia Makki, Edwin Aguilar

Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2019) · pp. 116-125, 2019

AI Security & PrivacyBlockchainCyber-Physical Systems & IoT
Paper ↗DOI ↗
BibTeX
@inproceedings{shield8,
  title = {Quantifying location privacy in permissioned blockchain-based internet of things (IoT)},
  author = {Abdur R. Shahid and Niki Pissinou and Laurent Njilla and Sheila Alemany and Ahmed Imteaj and Kia Makki and Edwin Aguilar},
  year = {2019},
  booktitle = {Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2019)},
  pages = {116-125},
  doi = {10.1145/3360774.3360800},
  url = {https://doi.org/10.1145/3360774.3360800}
}
Demo

Towards the development of a differentially private lightweight and scalable blockchain for IoT

Abdur R Shahid, Niki Pissinou, Laurent Njilla, Edwin Aguilar, Eric Perez

2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops (MASSW) · pp. 172-173, 2019

AI Security & PrivacyBlockchainCyber-Physical Systems & IoT
Paper ↗DOI ↗
BibTeX
@misc{shield9,
  title = {Towards the development of a differentially private lightweight and scalable blockchain for IoT},
  author = {Abdur R Shahid and Niki Pissinou and Laurent Njilla and Edwin Aguilar and Eric Perez},
  year = {2019},
  howpublished = {2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops (MASSW)},
  pages = {172-173},
  publisher = {IEEE},
  doi = {10.1109/massw.2019.00045},
  url = {https://doi.org/10.1109/massw.2019.00045}
}
Dissertation

Trajectory Privacy Preservation and Lightweight Blockchain Techniques for Mobility-Centric IoT

Abdur Bin Shahid

Florida International University · 2019

AI Security & PrivacyBlockchainCyber-Physical Systems & IoT
PDFPaper ↗
BibTeX
@phdthesis{shield12,
  title = {Trajectory Privacy Preservation and Lightweight Blockchain Techniques for Mobility-Centric IoT},
  author = {Abdur Bin Shahid},
  year = {2019},
  publisher = {Florida International University},
  url = {https://digitalcommons.fiu.edu/record/12960?ln=en}
}
TrustCom / BigDataSEConference

Check-ins and photos: Spatiotemporal correlation-based location inference attack and defense in location-based social networks

Abdur R Shahid, Niki Pissinou, SS Iyengar, Kia Makki

2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE) · pp. 1852-1857, 2018

AI Security & Privacy
Paper ↗DOI ↗
BibTeX
@inproceedings{shield3,
  title = {Check-ins and photos: Spatiotemporal correlation-based location inference attack and defense in location-based social networks},
  author = {Abdur R Shahid and Niki Pissinou and SS Iyengar and Kia Makki},
  year = {2018},
  booktitle = {2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE)},
  pages = {1852-1857},
  publisher = {IEEE},
  doi = {10.1109/trustcom/bigdatase.2018.00280},
  url = {https://doi.org/10.1109/trustcom/bigdatase.2018.00280}
}
Conference

KLAP for Real-World Protection of Location Privacy

Abdur R. Shahid, Niki Pissinou, S.S. Iyengar, Jerry Miller, Ziqian Ding, Teresita Lemus

2018 IEEE World Congress on Services · pp. 17-18, 2018

AI Security & Privacy
PDFPaper ↗DOI ↗
BibTeX
@inproceedings{shield2,
  title = {KLAP for Real-World Protection of Location Privacy},
  author = {Abdur R. Shahid and Niki Pissinou and S.S. Iyengar and Jerry Miller and Ziqian Ding and Teresita Lemus},
  year = {2018},
  booktitle = {2018 IEEE World Congress on Services},
  pages = {17-18},
  doi = {10.1109/services.2018.00022},
  url = {https://doi.org/10.1109/SERVICES.2018.00022}
}
Workshop

Reputation-Aware Data Fusion and Malicious Participant Detection in Mobile Crowdsensing

Yujian ‘Charles’ Tang*, Samia Tasnim, Niki Pissinou, S. S. Iyengar, Abdur Shahid

Workshop on Big Data for CyberSecurity (BigCyber-2018) · 2018

AI Security & PrivacyCyber-Physical Systems & IoT
Paper ↗DOI ↗
BibTeX
@inproceedings{shield4,
  title = {Reputation-Aware Data Fusion and Malicious Participant Detection in Mobile Crowdsensing},
  author = {Yujian ‘Charles’ Tang* and Samia Tasnim and Niki Pissinou and S. S. Iyengar and Abdur Shahid},
  year = {2018},
  booktitle = {Workshop on Big Data for CyberSecurity (BigCyber-2018)},
  doi = {10.1109/bigdata.2018.8622335},
  url = {https://doi.org/10.1109/bigdata.2018.8622335}
}
Conference

PPVC: Privacy Preserving Voronoi Cell for location-based services.

Abdur R. Shahid, Liz Jeukeng, Wei Zeng, Niki Pissinou, S. S. Iyengar, Sartaj Sahni, Maite Varela-Conover

2017 International Conference on Computing, Networking and Communications, ICNC 2017 · pp. 351-355, 2017

AI Security & Privacy
Paper ↗DOI ↗
BibTeX
@inproceedings{shield1,
  title = {PPVC: Privacy Preserving Voronoi Cell for location-based services.},
  author = {Abdur R. Shahid and Liz Jeukeng and Wei Zeng and Niki Pissinou and S. S. Iyengar and Sartaj Sahni and Maite Varela-Conover},
  year = {2017},
  booktitle = {2017 International Conference on Computing, Networking and Communications, ICNC 2017},
  pages = {351-355},
  publisher = {IEEE},
  doi = {10.1109/iccnc.2017.7876153},
  url = {https://doi.org/10.1109/iccnc.2017.7876153}
}