29 citations · 62 across the 27 of their papers we have counts for
5 papers · 1 filter
Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
Xiaomeng Hu, Pin-Yu Chen, Tsung-Yi Ho
As large language models (LLMs) become more integral to society and technology, ensuring their safety becomes essential. Jailbreak attacks exploit vulnerabilities to bypass safety…
Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models
Chaoyi Zhu, Zaitang Li, Renyi Yang +4
Watermarking becomes one of the pivotal solutions to trace and verify the origin of synthetic images generated by artificial intelligence models, but it is not free of risks. Recen…
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Lei Hsiung, Tianyu Pang, Yung-Chen Tang +4
Recent advancements in large language models (LLMs) have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. Howe…
Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
Chen Xiong, Zihao Wang, Rui Zhu +4
Large Language Models (LLMs) rely on massive training datasets, often including proprietary data, which raises concerns about unauthorized usage and copyright infringement. Existin…
CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
Chen Xiong, Pin-Yu Chen, Tsung-Yi Ho
Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attack…