activity
20242026
collaborators
Showing cs.CRShow all

5 papers · 1 filter

cs.CR2026

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

Xianglin Yang, Bryan Hooi, Gelei Deng +2

The known stylistic biases in LLM judges, such as a preference for verbosity or specific sentence structures, present an underexplored security vulnerability. In this work, we intr…

cs.CR2026

Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections

Xianglin Yang, Yufei He, Shuo Ji +2

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but crea…

cs.CR2026

LLM-enabled Applications Require System-Level Threat Monitoring

Yedi Zhang, Haoyu Wang, Xianglin Yang +2

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, h…

cs.CR2025

TraceAegis: Securing LLM-Based Agents via Hierarchical and Behavioral Anomaly Detection

Jiahao Liu, Bonan Ruan, Xianglin Yang +5

LLM-based agents have demonstrated promising adaptability in real-world applications. However, these agents remain vulnerable to a wide range of attacks, such as tool poisoning and…

cs.CR2025

Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning

Xianglin Yang, Gelei Deng, Jieming Shi +2

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses.…