11 papers
The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models
Yuting Tan, Yi Huang, Zhuo Li
Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common…
RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline
André V. Duarte, Xuying li, Bin Zeng +3
If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself…
LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation
Huizhen Shu, Xuying Li, Zhuo Li
Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comp…
The Resurgence of GCG Adversarial Attacks on Large Language Models
Yuting Tan, Xuying Li, Zhuo Li +2
Gradient-based adversarial prompting, such as the Greedy Coordinate Gradient (GCG) algorithm, has emerged as a powerful method for jailbreaking large language models (LLMs). In thi…
Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation
Huizhen Shu, Xuying Li, Qirui Wang +3
With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challeng…
OpenCUA: Open Foundations for Computer-Use Agents
Xinyuan Wang, Bowen Wang, Dunjie Lu +39
Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, cr…