5 papers
MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
Yuhao Wang, Shengfang Zhai, Guanghao Jin +3
Large Language Model (LLM)-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and…
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
Yuan Xin, Dingfan Chen, Linyi Yang +2
As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful ou…
ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents
Linyi Yang, Yixuan Weng
Current deep-research agents run in a ''fire-and-forget'' mode: once started, they give users no way to fix errors or add expert knowledge during execution. We present ResearStudio…
Anchored Supervised Fine-Tuning
He Zhu, Junyou Su, Peng Lai +4
Post-training of large language models involves a fundamental trade-off between supervised fine-tuning (SFT), which efficiently mimics demonstrations but tends to memorize, and rei…
CAP: Data Contamination Detection via Consistency Amplification
Yi Zhao, Jing Li, Linyi Yang
Large language models (LLMs) are widely used, but concerns about data contamination challenge the reliability of LLM evaluations. Existing contamination detection methods are often…