中文
相关论文

相关论文: Clear, Compelling Arguments: Rethinking the Founda…

200 篇论文

Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In…

计算机与社会 · 计算机科学 2025-03-10 Benjamin Hilton , Marie Davidsen Buhl , Tomek Korbak , Geoffrey Irving

As frontier artificial intelligence (AI) systems become more capable, it becomes more important that developers can explain why their systems are sufficiently safe. One way to do so is via safety cases: reports that make a structured…

计算机与社会 · 计算机科学 2024-10-30 Marie Davidsen Buhl , Gaurav Sett , Leonie Koessler , Jonas Schuett , Markus Anderljung

Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…

计算机与社会 · 计算机科学 2025-02-11 Stephen Barrett , Philip Fox , Joshua Krook , Tuneer Mondal , Simon Mylius , Alejandro Tlaie

Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured,…

计算机与社会 · 计算机科学 2024-11-14 Arthur Goemans , Marie Davidsen Buhl , Jonas Schuett , Tomek Korbak , Jessica Wang , Benjamin Hilton , Geoffrey Irving

Frontier artificial intelligence (AI) systems present both benefits and risks to society. Safety cases - structured arguments supported by evidence - are one way to help ensure the safe development and deployment of these systems. Yet the…

计算机与社会 · 计算机科学 2024-12-24 Carmen Cârlan , Francesca Gomez , Yohan Mathew , Ketana Krishna , René King , Peter Gebauer , Ben R. Smith

Safety cases, structured arguments that a system is acceptably safe, are becoming central to the governance of AI systems. Yet, traditional safety-case practices from aviation or nuclear engineering rely on well-specified system boundaries,…

软件工程 · 计算机科学 2026-03-09 Sung Une Lee , Liming Zhu , Md Shamsujjoha , Liming Dong , Qinghua Lu , Jieshan Chen , Lionel Briand

As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is…

计算机与社会 · 计算机科学 2024-03-20 Joshua Clymer , Nick Gabrieli , David Krueger , Thomas Larsen

We present our Balanced, Integrated and Grounded (BIG) argument for assuring the safety of AI systems. The BIG argument adopts a whole-system approach to constructing a safety case for AI systems of varying capability, autonomy and…

计算机与社会 · 计算机科学 2025-04-01 Ibrahim Habli , Richard Hawkins , Colin Paterson , Philippa Ryan , Yan Jia , Mark Sujan , John McDermid

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technological systems. Against the backdrop of the Cold War, the first…

计算机与社会 · 计算机科学 2025-04-22 Heidy Khlaaf , Sarah Myers West

An assurance case is a structured argument, typically produced by safety engineers, to communicate confidence that a critical or complex system, such as an aircraft, will be acceptably safe within its intended context. Assurance cases often…

计算机与社会 · 计算机科学 2023-06-07 Zoe Porter , Ibrahim Habli , John McDermid , Marten Kaas

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…

人工智能 · 计算机科学 2025-05-26 Marie Davidsen Buhl , Jacob Pfau , Benjamin Hilton , Geoffrey Irving

We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional critical systems, such as aircraft flight control. We analyse…

计算机与社会 · 计算机科学 2025-02-07 Robin Bloomfield , John Rushby

In the future, AI will increasingly find its way into systems that can potentially cause physical harm to humans. For such safety-critical systems, it must be demonstrated that their residual risk does not exceed what is acceptable. This…

人工智能 · 计算机科学 2022-02-14 Michael Kläs , Lisa Jöckel , Rasmus Adler , Jan Reich

As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from…

计算机与社会 · 计算机科学 2024-01-23 Inioluwa Deborah Raji , Roel Dobbe

As part of the Frontier AI Safety Commitments agreed to at the 2024 AI Seoul Summit, many AI developers agreed to publish a safety framework outlining how they will manage potential severe risks associated with their systems. This paper…

计算机与社会 · 计算机科学 2025-03-10 Marie Davidsen Buhl , Ben Bucknall , Tammy Masterson

As artificial intelligence systems grow more capable and autonomous, frontier AI development poses potential systemic risks that could affect society at a massive scale. Current practices at many AI labs developing these systems lack…

计算机与社会 · 计算机科学 2025-06-03 Aidan Kierans , Kaley Rittichier , Utku Sonsayar , Avijit Ghosh

Frontier AI both amplifies existing risks and introduces qualitatively novel challenges. Not only is there a notable lack of stable scientific consensus resulting from the rapid pace of technological change, but emerging frontier AI safety…

‹ 上一页 1 2 3 10 下一页 ›