Related papers: Auditing Games for Sandbagging

Artificial intelligence (AI) is increasingly intervening in our lives, raising widespread concern about its unintended and undeclared side effects. These developments have brought attention to the problem of AI auditing: the systematic…

Audits contribute to the trustworthiness of Learning Analytics (LA) systems that integrate Artificial Intelligence (AI) and may be legally required in the future. We argue that the efficacy of an audit depends on the auditability of the…

Audits are critical mechanisms for identifying the risks and limitations of deployed artificial intelligence (AI) systems. However, the effective execution of AI audits remains incredibly difficult, and practitioners often need to make use…

Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We…

Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…

Before deploying a black-box model in high-stakes problems, it is important to evaluate the model's performance on sensitive subpopulations. For example, in a recidivism prediction task, we may wish to identify demographic groups for which…

The widespread use of generative AI systems is coupled with significant ethical and social challenges. As a result, policymakers, academic researchers, and social advocacy groups have all called for such systems to be audited. However,…

The last decade has witnessed the proliferation of Deep Learning models in many applications, achieving unrivaled levels of predictive performance. Unfortunately, the black-box nature of Deep Learning models has posed unanswered questions…

Effective enforcement of laws and policies requires expending resources to prevent and detect offenders, as well as appropriate punishment schemes to deter violators. In particular, enforcement of privacy laws and policies in modern…

In this short note, we propose a unified framework that bridges three areas: (1) a flipped perspective on the Turing Test, the "dual Turing test", in which a human judge's goal is to identify an AI rather than reward a machine for…

As modern video games become increasingly complex, traditional manual testing methods are proving costly and inefficient, limiting the ability to ensure high-quality game experiences. While advancements in Artificial Intelligence (AI) offer…

AI systems are increasingly able to autonomously conduct realistic software engineering tasks, and may soon be deployed to automate machine learning (ML) R&D itself. Frontier AI systems may be deployed in safety-critical settings, including…

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges…

This paper investigates the interplay between sequential hypothesis testing (SHT) and adversarial decision-making in partially observable games, focusing on the deceptive strategies of red and blue teams. Inspired by Sun Zi's The Art of War…

As AI systems become increasingly capable, understanding their offensive cyber potential is critical for informed governance and responsible deployment. However, it's hard to accurately bound their capabilities, and some prior evaluations…

Routine operational use of sensitive data is often governed by law and regulation. For instance, in the medical domain, there are various statues at the state and federal level that dictate who is permitted to work with patients' records…

To evaluate the safety and usefulness of deployment protocols for untrusted AIs, AI Control uses a red-teaming exercise played between a protocol designer and an adversary. This paper introduces AI-Control Games, a formal decision-making…

Adversarial decision-making in partially observable multi-agent systems requires sophisticated strategies for both deception and counter-deception. This paper presents a sequential hypothesis testing (SHT)-driven framework that captures the…

As AI models tackle increasingly complex problems, ensuring reliable human oversight becomes more challenging due to the difficulty of verifying solutions. Approaches to scaling AI supervision include debate, in which two agents engage in…

Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly met by these approaches. Various methods have therefore been…