collaborators

13 papers

cs.LG2026

SafeSeek: Universal Attribution of Safety Circuits in Language Models

Miao Yu, Siyuan Fu, Moayad Aloqaily +6

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional co…

cs.CL2026

LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models

Wei Zhang, Lintong Du, Yuanhe Zhang +4

Despite the strong performance of Large Language Models (LLMs) on complex instruction-following tasks, precise control of output length remains a persistent challenge. Existing met…

cs.CR2026

MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents

Zhenhong Zhou, Yuanhe Zhang, Hongwei Cai +6

The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security misalignment: agents implicitly trus…

cs.CL2026

HearSay Benchmark: Do Audio LLMs Leak What They Hear?

Jin Wang, Liang Lin, Kaiwen Luo +8

While Audio Large Language Models (ALLMs) have achieved remarkable progress in understanding and generation, their potential privacy implications remain largely unexplored. This pa…

cs.CL2026

CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns

Zhenhong Zhou, Shilinlu Yan, Chuanpu Liu +3

Large language models (LLMs) are increasingly deployed in cost-sensitive and on-device scenarios, and safety guardrails have advanced mainly in English. However, real-world Chinese…

cs.SD2026

RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios

Yibo Zhang, Liang Lin, Kaiwen Luo +8

While Audio Large Models (ALMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaus…