collaborators

13 papers

cs.CR2026

Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

Yanting Wang, Chenlong Yin, Runpeng Geng +1

Prompt injection poses significant security risks to LLM agents. Efficient and effective red-teaming is therefore critical, both for evaluating these risks and for collecting train…

cs.CR2026

PIArena: A Platform for Prompt Injection Evaluation

Runpeng Geng, Chenlong Yin, Yanting Wang +2

Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community faces a critical gap: the l…

cs.CR2026

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Hengkai Ye, Zhechang Zhang, Jinyuan Jia +1

Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration expands LLM capabilities, it also in…

cs.CR2026

Evaluating LLM-based Personal Information Extraction and Countermeasures

Yupei Liu, Yuqi Jia, Jinyuan Jia +1

Automatically extracting personal information -- such as name, phone number, and email address -- from publicly available profiles at a large scale is a stepstone to many other sec…

cs.CR2026

EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method

Yanting Wang, Jinyuan Jia

Random subspace method has wide security applications such as providing certified defenses against adversarial and backdoor attacks, and building robustly aligned LLM against jailb…

cs.LG2026

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Chenlong Yin, Runpeng Geng, Yanting Wang +1

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against ad…