English
Related papers

Related papers: Password-Activated Shutdown Protocols for Misalign…

200 papers

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

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

Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threaten the reliability of deep learning systems in the wild. To…

Autonomous Driving (AD) systems rely on AI components to make safety and correct driving decisions. Unfortunately, today's AI algorithms are known to be generally vulnerable to adversarial attacks. However, for such AI component-level…

The most advanced future AI systems will first be deployed inside the frontier AI companies developing them. According to these companies and independent experts, AI systems may reach or even surpass human intelligence and capabilities by…

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…

Artificial Intelligence · Computer Science 2026-05-06 Ivaxi Sheth , Jan Wehner , Sahar Abdelnabi , Ruta Binkyte , Mario Fritz

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

Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…

Cryptography and Security · Computer Science 2026-02-12 Mohan Rajagopalan , Vinay Rao

As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…

Artificial Intelligence · Computer Science 2025-08-29 Donglin Wang , Weiyun Liang , Chunyuan Chen , Jing Xu , Yulong Fu

A red team simulates adversary attacks to help defenders find effective strategies to defend their systems in a real-world operational setting. As more enterprise systems adopt AI, red-teaming will need to evolve to address the unique…

Machine Learning · Computer Science 2025-09-16 Anusha Sinha , Keltin Grimes , James Lucassen , Michael Feffer , Nathan VanHoudnos , Zhiwei Steven Wu , Hoda Heidari

This paper presents a proposal for the governance of frontier AI systems through a hybrid public-private system. Private bodies, authorized and overseen by government, provide certifications to developers of frontier AI systems on an opt-in…

Computers and Society · Computer Science 2025-04-17 Dean W. Ball

AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety…

Frontier AI regulations primarily focus on systems deployed to external users, where deployment is more visible and subject to outside scrutiny. However, high-stakes applications can occur internally when companies deploy highly capable…

Artificial Intelligence · Computer Science 2026-02-17 Joe Kwon , Stephen Casper

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…

Computers and Society · Computer Science 2025-03-10 Benjamin Hilton , Marie Davidsen Buhl , Tomek Korbak , Geoffrey Irving

This paper examines the state of affairs on Frontier Safety Policies in light of capability progress and growing expectations held by government actors and AI safety researchers from these safety policies. It subsequently argues that FSPs…

Computers and Society · Computer Science 2025-01-29 Matteo Pistillo

The malicious use or malfunction of advanced general-purpose AI (GPAI) poses risks that, according to leading experts, could lead to the 'marginalisation or extinction of humanity.' To address these risks, there are an increasing number of…

Computers and Society · Computer Science 2025-03-26 Rebecca Scholefield , Samuel Martin , Otto Barten

Structured access is an emerging paradigm for the safe deployment of artificial intelligence (AI). Instead of openly disseminating AI systems, developers facilitate controlled, arm's length interactions with their AI systems. The aim is to…

Artificial Intelligence · Computer Science 2022-04-12 Toby Shevlane

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…

Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…

Computers and Society · Computer Science 2024-10-04 Hayley Clatterbuck , Clinton Castro , Arvo Muñoz Morán

Evaluating the safety of AI Systems is a pressing concern for organizations deploying them. In addition to the societal damage done by the lack of fairness of those systems, deployers are concerned about the legal repercussions and the…