Accelerating Greedy Coordinate Gradient via Probe Sampling
arxiv(2024)
摘要
Safety of Large Language Models (LLMs) has become a central issue given their
rapid progress and wide applications. Greedy Coordinate Gradient (GCG) is shown
to be effective in constructing prompts containing adversarial suffixes to
break the presumingly safe LLMs, but the optimization of GCG is time-consuming
and limits its practicality. To reduce the time cost of GCG and enable more
comprehensive studies of LLM safety, in this work, we study a new algorithm
called to accelerate the GCG algorithm. At the core
of the algorithm is a mechanism that dynamically determines how similar a
smaller draft model's predictions are to the target model's predictions for
prompt candidates. When the target model is similar to the draft model, we rely
heavily on the draft model to filter out a large number of potential prompt
candidates to reduce the computation time. Probe sampling achieves up to 5.6
times speedup using Llama2-7b and leads to equal or improved attack success
rate (ASR) on the AdvBench.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要