8 papers
AgenTEE: Confidential LLM Agent Execution on Edge Devices
Sina Abdollahi, Mohammad M Maheri, Javad Forough +5
Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their t…
ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs
Mohammad M Maheri, Sunil Cotterill, Alex Davidson +1
Machine unlearning aims to remove the influence of specific data points from a trained model to satisfy privacy, copyright, and safety requirements. In real deployments, providers…
WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols
Mohammad M Maheri, Xavier Cadet, Peter Chin +1
Approximate machine unlearning aims to efficiently remove the influence of specific data points from a trained model, offering a practical alternative to full retraining. However,…
Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning
Mohammad Mahdi Maheri, Denys Herasymuk, Hamed Haddadi
The growing adoption of Artificial Intelligence (AI) in Internet of Things (IoT) ecosystems has intensified the need for personalized learning methods that can operate efficiently…
GuardNet: Graph-Attention Filtering for Jailbreak Defense in Large Language Models
Javad Forough, Mohammad Maheri, Hamed Haddadi
Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful b…
Verifiable Unlearning on Edge
Mohammad M Maheri, Alex Davidson, Hamed Haddadi
Machine learning providers commonly distribute global models to edge devices, which subsequently personalize these models using local data. However, issues such as copyright infrin…