12 papers
Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization
Yuqin Lan, Gen Li, Yuanze Hu +6
Vision-Language Models (VLMs) are powerful but remain vulnerable to multimodal jailbreak attacks. Existing attacks mainly rely on either explicit visual prompt attacks or gradient-…
HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
Boshui Chen, Zhaoxin Fan, Ke Wang +5
Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection…
EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
Zhaoxin Fan, Nanxiang Jiang, Daiheng Gao +2
Removing undesired concepts from large-scale text-to-image (T2I) and text-to-video (T2V) diffusion models while preserving overall generative quality remains a major challenge, par…
The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
Zixuan Qin, Qingchen Yu, Kunlin Lyu +2
Large Language Models (LLMs) have become foundational tools in natural language processing, powering a wide range of applications and research. Many studies have shown that LLMs sh…
Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
Nanxiang Jiang, Zhaoxin Fan, Enhan Kang +6
Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to pro…
Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty
Zhichao Yang, Zhaoxin Fan, Gen Li +6
Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fal…