activity
20242026
collaborators

6 papers

cs.CL2026

GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs

Haibo Jin, Ruoxi Chen, Peiyan Zhang +3

As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted significant societal and regulatory conc…

cs.LG2025

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

Haibo Jin, Ruoxi Chen, Peiyan Zhang +2

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major s…

cs.AI2025

Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search

Andy Zhou, Ron Arel

We introduce Tempest, a multi-turn adversarial framework that models the gradual erosion of Large Language Model (LLM) safety through a tree search perspective. Unlike single-turn…

cs.CL2025

Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models

Andy Zhou

Adapting large language models to multiple tasks can cause cross-skill interference, where improvements for one skill degrade another. While methods such as LoRA impose orthogonali…

cs.LG2025

Tamper-Resistant Safeguards for Open-Weight LLMs

Rishub Tamirisa, Bhrugu Bharathi, Long Phan +12

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique chal…

cs.LG2024

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

Andy Zhou, Bo Li, Haohan Wang

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted…