activity
20242026
most citedRAG Security and Privacy: Formalizing the Threat Model and Attack Surface

2 citations · 2 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CR20262 cited

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Atousa Arzanipour, Rouzbeh Behnia, Reza Ebrahimi +1

Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external document retrieval to produce m…

cs.LG2026

Information Theoretic Adversarial Training of Large Language Models

Yiwei Zhang, Jeremiah Birrell, Reza Ebrahimi +3

Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies.…

cs.CR2025

Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security

Yiwei Zhang, Rouzbeh Behnia, Attila A. Yavuz +2

Federated learning (FL) enables collaborative model training while preserving user data privacy by keeping data local. Despite these advantages, FL remains vulnerable to privacy at…

cs.LG2025

An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models

Kasra Ahmadi, Rouzbeh Behnia, Reza Ebrahimi +4

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can rev…

cs.LG2024

From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models

Yuncong Yang, Xiao Han, Yidong Chai +3

Recent privacy regulations (e.g., GDPR) grant data subjects the `Right to Be Forgotten' (RTBF) and mandate companies to fulfill data erasure requests from data subjects. However, c…

cs.CR2024

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning

Yiwei Zhang, Rouzbeh Behnia, Attila A. Yavuz +2

Federated learning enables the collaborative learning of a global model on diverse data, preserving data locality and eliminating the need to transfer user data to a central server…