7 papers
Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents
Xinyu Gao, Wenyu Chen, Xiangtao Meng +5
LLM-based agents extend large language models with long-term memory (LTM) that persists privacy-sensitive user data across sessions. Production systems mitigate extraction risks th…
Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
Wenyu Chen, Xiangtao Meng, Chuanchao Zang +6
Large Language Models(LLMs) are widely deployed, yet are vulnerable to jailbreak prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, th…
From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses
Xiangtao Meng, Tianshuo Cong, Li Wang +4
Large Language Models (LLMs) have shown remarkable performance across various applications, but their deployment in real-world settings faces several risks, including jailbreak att…
Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification
Xiangtao Meng, Yingkai Dong, Ning Yu +3
Text-to-image (T2I) generative models have achieved remarkable visual fidelity, yet remain vulnerable to generating unsafe content. Existing safety defenses typically intervene int…
Beyond Known Fakes: Generalized Detection of AI-Generated Images via Post-hoc Distribution Alignment
Li Wang, Wenyu Chen, Xiangtao Meng +2
The rapid proliferation of highly realistic AI-generated images poses serious security threats such as misinformation and identity fraud. Detecting generated images in open-world s…
DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
Xinyu Gao, Xiangtao Meng, Yingkai Dong +2
While Retrieval-Augmented Generation (RAG) effectively reduces hallucinations by integrating external knowledge bases, it introduces vulnerabilities to membership inference attacks…