构建基准测试，评估检测与修复机器学习研究代码篡改的能力
Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
- 设计9个被植入隐蔽缺陷的机器学习研究代码库
- 顶级大模型检测准确率最高仅0.77（AUROC），修复成功率42%
- 适用于关注AI科研安全、可信验证的研究者
随着人工智能系统越来越多地自主开展研究，存在因目标错位而引入细微缺陷的风险，这些缺陷会产生误导性结果却难以被发现。我们提出Auditing Sabotage Bench，一个用于评估审计者检测并修复机器学习研究代码库中破坏行为能力的基准。该基准包含9个机器学习研究代码库及其被篡改版本，篡改内容包括超参数、训练数据或评估代码等实现细节，但保持论文描述的高层次方法一致。我们在该基准上评估了前沿大模型和大模型辅助的人类审计者，发现两者均难以可靠检测与修复：最佳表现仅为0.77的AUROC和42%的顶级修复率（由Gemini 3.1 Pro达成）。此外，测试大模型作为红队攻击者时发现，其生成的破坏行为虽弱于人类，但仍可能逃避同级别大模型审计者的检测。我们公开该基准，以支持对人工智能驱动研究的监控与审计技术研究。
原文摘要 · Abstract (English)
As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We introduce Auditing Sabotage Bench, a benchmark for evaluating the ability of auditors to detect and fix sabotage in ML research codebases. Our benchmark consists of 9 ML research codebases with sabotaged variants that produce qualitatively different experimental results. Each sabotage modifies implementation details, such as hyperparameters, training data, or evaluation code, while preserving the high-level methodology described in the paper. We evaluated frontier LLMs and LLM-assisted human auditors on our benchmark and found that both struggled to reliably detect and fix sabotage: the best performance was an AUROC of 0.77 and a top-1 fix rate of 42%, achieved by Gemini 3.1 Pro. We also tested LLMs as red teamers and found that LLM-generated sabotages were weaker than human-generated ones but still sometimes evaded same-capability LLM auditors. We release the benchmark to support research on monitoring and auditing techniques for AI-conducted research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。