4 papers
Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it
Hadi Reisizadeh, Jiajun Ruan, Sijia Liu +1
Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable content. In this work, we show tha…
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
Jiajun Ruan, Peiyang Li, Yukun Chen +2
The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to miti…
Leak@: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
Hadi Reisizadeh, Jiajun Ruan, Yiwei Chen +3
Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or cop…
NetArena: Dynamic Benchmarks for AI Agents in Network Automation
Yajie Zhou, Jiajun Ruan, Eric S. Wang +4
As AI agents expand into high-stakes domains like network system operations, evaluating their real-world reliability becomes increasingly critical. However, existing benchmarks ris…