Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

• URL: http://arxiv.org/abs/2407.21792v3
• Date: Fri, 27 Dec 2024 17:36:21 GMT
• Title: Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
• Authors: Richard Ren, Steven Basart, Adam Khoja, Alice Gatti, Long Phan, Xuwang Yin, Mantas Mazeika, Alexander Pan, Gabriel Mukobi, Ryan H. Kim, Stephen Fitz, Dan Hendrycks,
• Abstract summary: We propose an empirical foundation for developing more meaningful safety metrics and define AI safety in a machine learning research context. We aim to provide a more rigorous framework for AI safety research, advancing the science of safety evaluations and clarifying the path towards measurable progress.
• Score: 59.96471873997733
• License:
• Abstract: As artificial intelligence systems grow more powerful, there has been increasing interest in "AI safety" research to address emerging and future risks. However, the field of AI safety remains poorly defined and inconsistently measured, leading to confusion about how researchers can contribute. This lack of clarity is compounded by the unclear relationship between AI safety benchmarks and upstream general capabilities (e.g., general knowledge and reasoning). To address these issues, we conduct a comprehensive meta-analysis of AI safety benchmarks, empirically analyzing their correlation with general capabilities across dozens of models and providing a survey of existing directions in AI safety. Our findings reveal that many safety benchmarks highly correlate with both upstream model capabilities and training compute, potentially enabling "safetywashing"--where capability improvements are misrepresented as safety advancements. Based on these findings, we propose an empirical foundation for developing more meaningful safety metrics and define AI safety in a machine learning research context as a set of clearly delineated research goals that are empirically separable from generic capabilities advancements. In doing so, we aim to provide a more rigorous framework for AI safety research, advancing the science of safety evaluations and clarifying the path towards measurable progress.

Related papers

• Computational Safety for Generative AI: A Signal Processing Perspective [65.268245109828]
  computational safety is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI. We show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts. We discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.
  arXiv  Detail & Related papers  (2025-02-18T02:26:50Z)
• AI Safety for Everyone [3.440579243843689]
  Recent discussions and research in AI safety have increasingly emphasized the deep connection between AI safety and existential risk from advanced AI systems. This framing may exclude researchers and practitioners who are committed to AI safety but approach the field from different angles. We find a vast array of concrete safety work that addresses immediate and practical concerns with current AI systems.
  arXiv  Detail & Related papers  (2025-02-13T13:04:59Z)
• SafetyAnalyst: Interpretable, transparent, and steerable safety moderation for AI behavior [56.10557932893919]
  We present SafetyAnalyst, a novel AI safety moderation framework. Given an AI behavior, SafetyAnalyst uses chain-of-thought reasoning to analyze its potential consequences. It aggregates all harmful and beneficial effects into a harmfulness score using fully interpretable weight parameters.
  arXiv  Detail & Related papers  (2024-10-22T03:38:37Z)
• Trustworthy, Responsible, and Safe AI: A Comprehensive Architectural Framework for AI Safety with Challenges and Mitigations [15.946242944119385]
  AI Safety is an emerging area of critical importance to the safe adoption and deployment of AI systems. Our goal is to promote advancement in AI safety research, and ultimately enhance people's trust in digital transformation.
  arXiv  Detail & Related papers  (2024-08-23T09:33:48Z)
• Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model [73.8765529028288]
  We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment. To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations. Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-21T16:14:15Z)
• Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems [88.80306881112313]
  We will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI. The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees. We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them.
  arXiv  Detail & Related papers  (2024-05-10T17:38:32Z)
• Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements [76.80453043969209]
  This survey presents a framework for safety research pertaining to large models. We begin by introducing safety issues of wide concern, then delve into safety evaluation methods for large models. We explore the strategies for enhancing large model safety from training to deployment.
  arXiv  Detail & Related papers  (2023-02-18T09:32:55Z)
• On Safety Assessment of Artificial Intelligence [0.0]
  We show that many models of artificial intelligence, in particular machine learning, are statistical models. Part of the budget of dangerous random failures for the relevant safety integrity level needs to be used for the probabilistic faulty behavior of the AI system. We propose a research challenge that may be decisive for the use of AI in safety related systems.
  arXiv  Detail & Related papers  (2020-02-29T14:05:28Z)
• TanksWorld: A Multi-Agent Environment for AI Safety Research [5.218815947097599]
  The ability to create artificial intelligence capable of performing complex tasks is rapidly outpacing our ability to ensure the safe and assured operation of AI-enabled systems. Recent simulation environments to illustrate AI safety risks are relatively simple or narrowly-focused on a particular issue. We introduce the AI safety TanksWorld as an environment for AI safety research with three essential aspects.
  arXiv  Detail & Related papers  (2020-02-25T21:00:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.