English
Related papers

Related papers: Evaluating whether AI models would sabotage AI saf…

200 papers

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…

Computers and Society · Computer Science 2026-05-01 Lily Stelling , Malcolm Murray , Bruno Galizzi , Max Schaffelder , Siméon Campos , Henry Papadatos

This paper contributes to the nascent debate around safety cases for frontier AI systems. Safety cases are structured, defensible arguments that a system is acceptably safe to deploy in a given context. Historically, they have been used in…

Computers and Society · Computer Science 2026-03-11 Shaun Feakins , Ibrahim Habli , Phillip Morgan

As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We introduce…

Cryptography and Security · Computer Science 2026-05-29 Nikolay Radev , Lennart Haas , Benjamin Arnav , Pablo Bernabeu-Pérez

AI evaluations are an important component of the AI governance toolkit, underlying current approaches to safety cases for preventing catastrophic risks. Our paper examines what these evaluations can and cannot tell us. Evaluations can…

Computers and Society · Computer Science 2024-12-13 Peter Barnett , Lisa Thiergart

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been proposed to mitigate these attacks, the heterogeneous…

Cryptography and Security · Computer Science 2025-11-18 Gorka Abad , Marina Krček , Stefanos Koffas , Behrad Tajalli , Marco Arazzi , Roberto Riaño , Xiaoyun Xu , Zhuoran Liu , Antonino Nocera , Stjepan Picek

Frontier AI companies first deploy their most advanced models internally, for weeks or months of safety testing, evaluation, and iteration, before a possible public release. For example, Anthropic recently developed a new class of model…

Computers and Society · Computer Science 2026-04-30 Oscar Delaney , Sambhav Maheshwari , Joe O'Brien , Theo Bearman , Oliver Guest

Evaluating AI-generated reviews by verdict agreement is widely recognized as insufficient, yet current alternatives rarely audit which concerns a system identifies, how it prioritizes them, or whether those priorities align with the review…

Artificial Intelligence · Computer Science 2026-04-23 Ming Jin

As Artificial Intelligence (AI) systems proliferate, the need for systematic, transparent, and actionable processes for evaluating them is growing. While many resources exist to support AI evaluation, they have several limitations. Few…

Computers and Society · Computer Science 2026-02-02 Rachel M. Kim , Blaine Kuehnert , Alice Lai , Kenneth Holstein , Hoda Heidari , Rayid Ghani

Embedding artificial intelligence into systems introduces significant challenges to modern engineering practices. Hazard analysis tools and processes have not yet been adequately adapted to the new paradigm. This paper describes initial…

Software Engineering · Computer Science 2022-03-30 Nikolas Martelaro , Carol J. Smith , Tamara Zilovic

This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how…

Computers and Society · Computer Science 2026-01-23 Don Hickerson , Mike Perkins

We study whether state-of-the-art AI coding agents, given the same data and research question, produce the same empirical results. Deploying 150 autonomous Claude Code agents to independently test six hypotheses about market quality trends…

Artificial Intelligence · Computer Science 2026-03-20 Ruijiang Gao , Steven Chong Xiao

Frontier AI Safety Policies concentrate on prevention: capability evaluations, deployment gates, and usage constraints, while neglecting the capacity to coordinate responses when prevention fails. We argue this coordination gap is…

Computers and Society · Computer Science 2026-05-21 Isaak Mengesha

We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training. First, we give Claude 3 Opus a system…

As AI systems approach dangerous capability levels where inability safety cases become insufficient, we need alternative approaches to ensure safety. This paper presents a roadmap for constructing safety cases based on chain-of-thought…

Machine Learning · Computer Science 2025-10-23 Julian Schulz

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…

Artificial Intelligence · Computer Science 2025-10-14 Leonard Dung , Florian Mai

This paper presents an argument that certain AI safety measures, rather than mitigating existential risk, may instead exacerbate it. Under certain key assumptions - the inevitability of AI failure, the expected correlation between an AI…

Artificial Intelligence · Computer Science 2024-06-04 Herman Cappelen , Josh Dever , John Hawthorne

Construction remains one of the most hazardous sectors. Recent advancements in AI, particularly Large Language Models (LLMs), offer promising opportunities for enhancing workplace safety. However, responsible integration of LLMs requires…

Artificial Intelligence · Computer Science 2024-11-14 Farouq Sammour , Jia Xu , Xi Wang , Mo Hu , Zhenyu Zhang

The $\textit{LLM-as-a-judge}$ paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: that judges evaluate text strictly on its semantic content, impervious to surrounding…

Artificial Intelligence · Computer Science 2026-04-17 Manan Gupta , Inderjeet Nair , Lu Wang , Dhruv Kumar

AI tools are being deployed over MBSE models today, and those models were not designed for this kind of consumption. The problem is not simply that tools hallucinate: well-prompted frontier models produce competent, useful output over a…

Software Engineering · Computer Science 2026-04-29 Siyuan Ji

Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in their standard form, but they often fail when the same problems are posed in logically…

Computation and Language · Computer Science 2026-02-03 Abhilekh Borah , Shubhra Ghosh , Kedar Joshi , Aditya Kumar Guru , Kripabandhu Ghosh
‹ Prev 1 3 4 5 6 7 10 Next ›