用于 LLM 鲁棒性评估的快速代理指标
Fast Proxies for LLM Robustness Evaluation
AI总结:
本文研究 LLM 对抗鲁棒性评估成本过高的问题,提出用快速代理指标预测完整攻击集合下的攻击成功率,并验证其可在保持高相关性的同时将计算成本降低三个数量级。
摘要:
评估 LLM 对对抗攻击的鲁棒性对于安全部署至关重要,但当前的红队方法往往成本高得令人难以承受。我们比较了快速代理指标预测 LLM 面对模拟攻击者集合时真实鲁棒性的能力。这使我们能够估计模型对计算成本高昂攻击的鲁棒性,而无需实际运行这些攻击。具体而言,我们考虑了基于梯度下降的嵌入空间攻击、预填充攻击和直接提示。尽管直接提示尤其未能实现较高的 ASR,但我们发现它与嵌入空间攻击能够很好地预测攻击成功率,在与完整攻击集合的相关性上达到 $r_p=0.87$(线性)和 $r_s=0.94$(Spearman 秩),同时将计算成本降低三个数量级。
英文摘要:
Evaluating the robustness of LLMs to adversarial attacks is crucial for safe deployment, yet current red-teaming methods are often prohibitively expensive. We compare the ability of fast proxy metrics to predict the real-world robustness of an LLM against a simulated attacker ensemble. This allows us to estimate a model's robustness to computationally expensive attacks without requiring runs of the attacks themselves. Specifically, we consider gradient-descent-based embedding-space attacks, prefilling attacks, and direct prompting. Even though direct prompting in particular does not achieve high ASR, we find that it and embedding-space attacks can predict attack success rates well, achieving $r_p=0.87$ (linear) and $r_s=0.94$ (Spearman rank) correlations with the full attack ensemble while reducing computational cost by three orders of magnitude.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。