6 papers
Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks
Mingyu Luo, Ming Deng, Zilang Qiu +8
Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones. That separation is then read…
When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems
Haowen Xu, Xue Tan, Lei Ma +6
While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction l…
EMPalm: Exfiltrating Palm Biometric Data via Electromagnetic Side-Channel
Haowen Xu, Tianya Zhao, Xuyu Wang +4
Palm recognition has emerged as a dominant biometric authentication technology in critical infrastructure. These systems operate in either single-modal form, using palmprint or pal…
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption
Xue Tan, Yi Zheng, Chang Huo +7
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, effectively mitigating their inherent knowledge limitations. However…
Generalizable and Interpretable RF Fingerprinting with Shapelet-Enhanced Large Language Models
Tianya Zhao, Junqing Zhang, Haowen Xu +3
Deep neural networks (DNNs) have achieved remarkable success in radio frequency (RF) fingerprinting for wireless device authentication. However, their practical deployment faces tw…
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
Xue Tan, Hao Luan, Mingyu Luo +3
Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database, enabling them to produce responses that are more acc…