Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
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 benchm...
| Authors | Eric Gan, Aryan Bhatt, Buck Shlegeris et al. |
|---|---|
| Primary category | cs.AI |
| Published | 17 April 2026 |
| Last updated at source | 26 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.