English
Related papers

Related papers: Quantifying detection rates for dangerous capabili…

200 papers

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

Artificial Intelligence · Computer Science 2025-05-12 Markov Grey , Charbel-Raphaël Segerie

Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe before they can be developed or deployed. The goal of this paper is to expand on this idea and explore…

Computers and Society · Computer Science 2024-06-25 Akash R. Wasil , Joshua Clymer , David Krueger , Emily Dardaman , Simeon Campos , Evan R. Murphy

Frontier AI systems are being adopted across Africa, yet most AI safety evaluations are designed and validated in Western environments. In this paper, we argue that the portability gap can leave Africa-centric pathways to severe harm…

Risk assessments for advanced AI systems require evaluating both the models themselves and their deployment contexts. We introduce the Societal Capacity Assessment Framework (SCAF), an indicators-based approach to measuring a society's…

Computers and Society · Computer Science 2025-09-30 Milan Gandhi , Peter Cihon , Owen Larter , Rebecca Anselmetti

We examine how the federal government can enhance its AI emergency preparedness: the ability to detect and prepare for time-sensitive national security threats relating to AI. Emergency preparedness can improve the government's ability to…

Computers and Society · Computer Science 2024-07-30 Akash Wasil , Everett Smith , Corin Katzke , Justin Bullock

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

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider…

Artificial Intelligence · Computer Science 2025-06-17 Yoshua Bengio , Michael K. Cohen , Nikolay Malkin , Matt MacDermott , Damiano Fornasiere , Pietro Greiner , Younesse Kaddar

Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI…

Cryptography and Security · Computer Science 2026-03-17 Simone Aonzo , Merve Sahin , Aurélien Francillon , Daniele Perito

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated…

Computers and Society · Computer Science 2024-03-13 Heather M. Williams , Roman V. Yampolskiy

With AI-based software becoming widely available, the risk of exploiting its capabilities, such as high automation and complex pattern recognition, could significantly increase. An AI used offensively to attack non-AI assets is referred to…

Cryptography and Security · Computer Science 2025-04-08 Anket Mehra , Andreas Aßmuth , Malte Prieß

Frontier AI companies increasingly rely on external evaluations to assess risks from dangerous capabilities before deployment. However, external evaluators often receive limited model access, limited information, and little time, which can…

Computers and Society · Computer Science 2026-01-21 Jacob Charnock , Alejandro Tlaie , Kyle O'Brien , Stephen Casper , Aidan Homewood

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

Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to reason step-by-step and inference-time enhancements have…

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…

Computers and Society · Computer Science 2025-06-03 Aidan Kierans , Kaley Rittichier , Utku Sonsayar , Avijit Ghosh

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,…

Computers and Society · Computer Science 2024-11-14 Arthur Goemans , Marie Davidsen Buhl , Jonas Schuett , Tomek Korbak , Jessica Wang , Benjamin Hilton , Geoffrey Irving

The governance of frontier general-purpose artificial intelligence has become a public-sector problem of institutional design, not merely a technical issue of model performance. Recent evidence indicates that AI capabilities are advancing…

Computers and Society · Computer Science 2026-04-09 Fabio Correa Xavier

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,…

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…

Artificial Intelligence · Computer Science 2024-07-15 John Burden

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…

Computers and Society · Computer Science 2023-10-03 Joe O'Brien , Shaun Ee , Zoe Williams

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…