Keshav Shenoy, Anthony Zang, Eric Gan, Jacqueline Tay, Amy Ngo, Sebastian Prasanna, Julian Stastny, Vivek Hebbar
原文摘要
As AI systems are increasingly used to automate AI R&D, misaligned systems could sabotage research intended to improve model safety and alignment. To stress-test defenses against such sabotage, we use a human expert as a proxy saboteur on AI safety research. We conduct a red-team/blue-team game where a human researcher runs AI safety experiments from scratch and auditors try to tell which were sabotaged and how. Given access to the full research transcript and the ability to run experiments, human auditors mostly fail to distinguish sabotaged from benign research: they achieve an AUROC of 0.59, not significantly better than chance, and fully identify the specific sabotage in only 17% of cases. Despite not being allowed to run experiments, the best frontier models outperform human auditors (Fable 5.1: AUROC 0.73, 32% full identification) within noise and weaker models perform comparably. When the saboteur chooses which experiments are attacked, rather than being required to sabotage every question given, sabotage identification drops further. Our results suggest that research sabotage by expert-level agents is difficult to detect with current auditing methods and provide a new setting for studying research sabotage.
Mikhail Terekhov, Caglar Gulcehre, Vivek Hebbar, Joe Benton
原文摘要
AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment. Diffuse AI Control is a subfield of AI safety concerned with mitigating risks from AI sabotage distributed over long deployment horizons (diffuse threats). These risks are particularly pernicious on fuzzy tasks, i.e. tasks which are hard to grade or require intuition. To understand diffuse threats on fuzzy tasks, we introduce a framework that considers AI control as an adversarial game between a blue team and a red team. The blue team uses a weak trusted model to construct a weak score against which they would train a strong, potentially subversive model to remove the subversion propensity if it were present. The red team then tries to find model behaviors that are rated highly by the weak score, and thus might not be trained out, but actually correspond to poor performance. We test our framework on the task of writing experimental proposals for research questions from recent ML papers. We use a language model with access to the original paper as a proxy "ground-truth" scorer. Our red team discovers subversive behaviors using multi-objective evolutionary prompt optimization. We show that Opus~4.6 can write proposals that are worse according to the ground truth proxy than those of GPT-OSS-20B, while the weak scorer rates them as highly as the best proposals from Opus 4.6. We then propose an adversarial optimization algorithm for the blue team that discovers more robust prompts for the weak model. This algorithm produces a blue team prompt that our red team optimization fails to exploit. Code is available at https://github.com/MikhailTerekhov/diffuse_control.