中文
相关论文

相关论文: Safetywashing: Do AI Safety Benchmarks Actually Me…

200 篇论文

The potential presented by Artificial Intelligence (AI) for healthcare has long been recognised by the technical community. More recently, this potential has been recognised by policymakers, resulting in considerable public and private…

人工智能 · 计算机科学 2021-04-15 Jessica Morley , Caroline Morton , Kassandra Karpathakis , Mariarosaria Taddeo , Luciano Floridi

The number and importance of AI-based systems in all domains is growing. With the pervasive use and the dependence on AI-based systems, the quality of these systems becomes essential for their practical usage. However, quality assurance for…

软件工程 · 计算机科学 2023-08-02 Michael Felderer , Rudolf Ramler

Digital technologies have dramatically accelerated the digital transformation in process industries, boosted new industrial applications, upgraded the production system, and enhanced operational efficiency. In contrast, the challenges and…

人机交互 · 计算机科学 2023-05-30 He Wen

AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and…

人工智能 · 计算机科学 2026-05-06 Ivaxi Sheth , Jan Wehner , Sahar Abdelnabi , Ruta Binkyte , Mario Fritz

Building trust in AI-based systems is deemed critical for their adoption and appropriate use. Recent research has thus attempted to evaluate how various attributes of these systems affect user trust. However, limitations regarding the…

人机交互 · 计算机科学 2022-04-29 Michaela Benk , Suzanne Tolmeijer , Florian von Wangenheim , Andrea Ferrario

The automation of AI R&D (AIRDA) could have significant implications, but its extent and ultimate effects remain uncertain. We need empirical data to resolve these uncertainties, but existing data (primarily capability benchmarks) may not…

计算机与社会 · 计算机科学 2026-03-09 Alan Chan , Ranay Padarath , Joe Kwon , Hilary Greaves , Markus Anderljung

As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…

密码学与安全 · 计算机科学 2025-05-13 Krti Tallam

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…

计算与语言 · 计算机科学 2026-05-28 Katharina Deckenbach , Haritz Puerto , Jonas Geiping , Sahar Abdelnabi

Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…

计算机与社会 · 计算机科学 2025-09-24 Luis Enriquez Alvarez

Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increasingly cited in global governance frameworks. This position paper argues that current implementations risk serving as symbolic…

密码学与安全 · 计算机科学 2026-03-04 Alexander Nemecek , Yuzhou Jiang , Erman Ayday

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…

计算机与社会 · 计算机科学 2026-02-24 Nelu D. Radpour

Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats…

计算机与社会 · 计算机科学 2026-05-01 Lily Stelling , Malcolm Murray , Bruno Galizzi , Max Schaffelder , Siméon Campos , Henry Papadatos

When training powerful AI systems to perform complex tasks, it may be challenging to provide training signals which are robust to optimization. One concern is \textit{measurement tampering}, where the AI system manipulates multiple…

机器学习 · 计算机科学 2023-10-02 Fabien Roger , Ryan Greenblatt , Max Nadeau , Buck Shlegeris , Nate Thomas

As AI assistants become integrated into safety engineering workflows for Physical AI systems, a critical question emerges: does AI assistance improve safety analysis quality, or introduce systematic blind spots that surface only through…

人工智能 · 计算机科学 2026-03-30 Umair Siddique

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented…

人工智能 · 计算机科学 2022-05-27 Bo Li , Peng Qi , Bo Liu , Shuai Di , Jingen Liu , Jiquan Pei , Jinfeng Yi , Bowen Zhou

While games have been used extensively as milestones to evaluate game-playing AI, there exists no standardised framework for reporting the obtained observations. As a result, it remains difficult to draw general conclusions about the…

人工智能 · 计算机科学 2020-07-07 Vanessa Volz , Boris Naujoks

Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increases in capabilities and autonomy may soon massively amplify…

Artificial intelligence (AI) is increasingly being used to augment and automate cyber operations, altering the scale, speed, and accessibility of malicious activity. These shifts raise urgent questions about when AI systems introduce…

密码学与安全 · 计算机科学 2026-01-27 Krystal Jackson , Deepika Raman , Jessica Newman , Nada Madkour , Charlotte Yuan , Evan R. Murphy

As AI systems appear to exhibit ever-increasing capability and generality, assessing their true potential and safety becomes paramount. This paper contends that the prevalent evaluation methods for these systems are fundamentally…

人工智能 · 计算机科学 2024-07-15 John Burden

More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of artificial intelligence (AI) systems. However, these benchmarks are often flawed and many aspects of common sense…

人工智能 · 计算机科学 2023-02-24 Ernest Davis