English
Related papers

Related papers: What AI evaluations for preventing catastrophic ri…

200 papers

To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations…

Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose catastrophic risks. Although numerous risks…

Computers and Society · Computer Science 2023-10-11 Dan Hendrycks , Mantas Mazeika , Thomas Woodside

Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to…

Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful…

Computers and Society · Computer Science 2026-03-31 Michelle Vaccaro , Jaeyoon Song , Abdullah Almaatouq , Michiel A. Bakker

As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a…

The advent of advanced AI underscores the urgent need for comprehensive safety evaluations, necessitating collaboration across communities (i.e., AI, software engineering, and governance). However, divergent practices and terminologies…

Software Engineering · Computer Science 2024-05-17 Boming Xia , Qinghua Lu , Liming Zhu , Zhenchang Xing

The rapid development of AI systems poses unprecedented risks, including loss of control, misuse, geopolitical instability, and concentration of power. To navigate these risks and avoid worst-case outcomes, governments may proactively…

Artificial Intelligence · Computer Science 2025-07-15 Peter Barnett , Aaron Scher , David Abecassis

Rapidly advancing artificial intelligence (AI) systems introduce novel, uncertain, and potentially catastrophic risks. Managing these risks requires a mature risk-management infrastructure whose cornerstone is rigorous risk modeling. We…

Oversight and control, which we collectively call supervision, are often discussed as ways to ensure that AI systems are accountable, reliable, and able to fulfill governance and management requirements. However, the requirements for "human…

Artificial Intelligence · Computer Science 2025-11-04 David Manheim , Aidan Homewood

Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a…

We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We…

Artificial Intelligence · Computer Science 2024-12-23 Paolo Bova , Alessandro Di Stefano , The Anh Han

The rapid advancement of AI systems has raised widespread concerns about potential harms of frontier AI systems and the need for responsible evaluation and oversight. In this position paper, we argue that frontier AI companies should report…

Computers and Society · Computer Science 2025-03-25 Dillon Bowen , Ann-Kathrin Dombrowski , Adam Gleave , Chris Cundy

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…

Computers and Society · Computer Science 2025-02-07 Robin Bloomfield , John Rushby

Artificial Intelligence (AI) is rapidly being integrated into critical systems across various domains, from healthcare to autonomous vehicles. While its integration brings immense benefits, it also introduces significant risks, including…

Computers and Society · Computer Science 2025-06-25 Zhiqiang Lin , Huan Sun , Ness Shroff

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…

Computers and Society · Computer Science 2024-10-30 Marie Davidsen Buhl , Gaurav Sett , Leonie Koessler , Jonas Schuett , Markus Anderljung

Artificial intelligence develops techniques and systems whose performance must be evaluated on a regular basis in order to certify and foster progress in the discipline. We will describe and critically assess the different ways AI systems…

Artificial Intelligence · Computer Science 2016-08-23 Jose Hernandez-Orallo

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…

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

Artificial Intelligence · Computer Science 2025-02-10 Teun van der Weij , Felix Hofstätter , Ollie Jaffe , Samuel F. Brown , Francis Rhys Ward

Frontier AI developers operate at the intersection of rapid technical progress, extreme risk exposure, and growing regulatory scrutiny. While a range of external evaluations and safety frameworks have emerged, comparatively little attention…

Computers and Society · Computer Science 2025-12-19 Francesca Gomez , Adam Buick , Leah Ferentinos , Haelee Kim , Elley Lee

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…

Computers and Society · Computer Science 2025-09-24 Luis Enriquez Alvarez