4 citations · 12 across the 10 of their papers we have counts for
4 papers · 1 filter
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
Kejia Chen, Jiawen Zhang, Boheng Li +6
Many-shot jailbreaking (MSJ) causes safety-aligned language models to answer harmful queries by preceding them with many harmful question-answer demonstrations. We study why this a…
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
Xingjun Ma, Yifeng Gao, Yixu Wang +45
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artifici…
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
Yi Zeng, Weiyu Sun, Tran Ngoc Huynh +3
Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionali…
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
Zhuowen Yuan, Zidi Xiong, Yi Zeng +4
Recent advancements in Large Language Models (LLMs) have showcased remarkable capabilities across various tasks in different domains. However, the emergence of biases and the poten…