Mohammad Maheri

According to our database, Mohammad Maheri authored at least 12 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

AgenTEE: Confidential LLM Agent Execution on Edge Devices.

Sina Abdollahi, Mohammad Mahdi Maheri, Javad Forough, Amir Al Sadi, Josh Millar, David Kotz, Marios Kogias, Hamed Haddadi

CoRR, April, 2026

Towards Graph-Based Detection of Jailbreak and Prompt-Leakage Attacks in LLMs.

Javad Forough, Mohammad Mahdi Maheri, Hamed Haddadi

Proceedings of the Sixth European Workshop on Machine Learning and Systems, EuroMLSys 2026, 2026

<i>AgenTEE: </i> Confidential LLM Agent Execution on Edge Devices.

Sina Abdollahi, Mohammad Mahdi Maheri, Javad Forough, Amir Al Sadi, Josh Millar, David Kotz, Marios Kogias, Hamed Haddadi

Proceedings of the Sixth European Workshop on Machine Learning and Systems, EuroMLSys 2026, 2026

2025

ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs.

Mohammad Mahdi Maheri, Sunil Cotterill, Alex Davidson, Hamed Haddadi

CoRR, December, 2025

Teleportation-Based Defenses for Privacy in Approximate Machine Unlearning.

Mohammad Mahdi Maheri, Xavier F. Cadet, Peter Chin, Hamed Haddadi

CoRR, December, 2025

GuardNet: Graph-Attention Filtering for Jailbreak Defense in Large Language Models.

Javad Forough, Mohammad Maheri, Hamed Haddadi

CoRR, September, 2025

Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning.

Mohammad Mahdi Maheri, Denys Herasymuk, Hamed Haddadi

CoRR, June, 2025

Verifiable Unlearning on Edge.

Mohammad Mahdi Maheri, Alex Davidson, Hamed Haddadi

CoRR, June, 2025

TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks.

Mohammad Mahdi Maheri, Hamed Haddadi, Alex Davidson

Proc. Priv. Enhancing Technol., 2025

An Early Experience With Confidential Computing Architecture for On-Device Model Protection.

Sina Abdollahi, Mohammad Maheri, Sandra Deepthy Siby, Marios Kogias, Hamed Haddadi

Proceedings of the IEEE European Symposium on Security and Privacy, 2025

2024

P4: Towards private, personalized, and Peer-to-Peer learning.

Mohammad Mahdi Maheri, Sandra Deepthy Siby, Sina Abdollahi, Anastasia Borovykh, Hamed Haddadi

CoRR, 2024

GuaranTEE: Towards Attestable and Private ML with CCA.

Sandra Deepthy Siby, Sina Abdollahi, Mohammad Maheri, Marios Kogias, Hamed Haddadi

Proceedings of the 4th Workshop on Machine Learning and Systems, 2024