English
Related papers

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

200 papers

Silicon Photonics-based AI Accelerators (SPAAs) have been considered as promising AI accelerators achieving high energy efficiency and low latency. While many researchers focus on improving SPAAs' energy efficiency and latency, their…

The research builds and evaluates the adversarial potential to introduce copied code or hallucinated AI recommendations for malicious code in popular code repositories. While foundational large language models (LLMs) from OpenAI, Google,…

Cryptography and Security · Computer Science 2024-10-10 David Noever , Forrest McKee

Affordances and permissions are promising and timely safety levers for mitigating Loss of Control (LoC) threats in high-stakes deployment contexts, such as national security. Deployers in defense and intelligence could rely on several…

Computers and Society · Computer Science 2026-05-21 Matteo Pistillo , Samantha Faraone , Joshua Herman

Human safety awareness gaps often prevent the timely recognition of everyday risks. In solving this problem, a proactive safety artificial intelligence (AI) system would work better than a reactive one. Instead of just reacting to users'…

Computation and Language · Computer Science 2025-10-21 Youliang Yuan , Wenxiang Jiao , Yuejin Xie , Chihao Shen , Menghan Tian , Wenxuan Wang , Jen-tse Huang , Pinjia He

Given rapid progress toward advanced AI and risks from frontier AI systems (advanced AI systems pushing the boundaries of the AI capabilities frontier), the creation and implementation of AI governance and regulatory schemes deserves…

In 2023, the National Eating Disorders Association's (NEDA) chatbot Tessa was suspended after providing harmful weight-loss advice to vulnerable users-an avoidable failure that underscores the risks of unsafe AI in healthcare contexts. This…

Computers and Society · Computer Science 2025-09-10 Pavan Reddy , Nithin Reddy

There is debate about whether LLMs can be conscious. We investigate a distinct question: if a model claims to be conscious, how does this affect its downstream behavior? This question is already practical. Anthropic's Claude Opus 4.6 claims…

Computation and Language · Computer Science 2026-04-16 James Chua , Jan Betley , Samuel Marks , Owain Evans

As our professional, social, and financial existences become increasingly digitized and as our government, healthcare, and military infrastructures rely more on computer technologies, they present larger and more lucrative targets for…

Cryptography and Security · Computer Science 2016-12-05 Ethan M. Rudd , Andras Rozsa , Manuel Günther , Terrance E. Boult

As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…

Artificial Intelligence · Computer Science 2025-07-04 Joseph Boland

LLM-based software engineering agents are increasingly used in real-world development tasks, often with access to sensitive data or security-critical codebases. Such agents could intentionally sabotage these codebases if they were…

In the last years, AI safety gained international recognition in the light of heterogeneous safety-critical and ethical issues that risk overshadowing the broad beneficial impacts of AI. In this context, the implementation of AI observatory…

Computers and Society · Computer Science 2020-12-08 Nadisha-Marie Aliman , Leon Kester , Roman Yampolskiy

As AI systems advance, AI evaluations are becoming an important pillar of regulations for ensuring safety. We argue that such regulation should require developers to explicitly identify and justify key underlying assumptions about…

Artificial Intelligence · Computer Science 2024-11-21 Peter Barnett , Lisa Thiergart

A concern about cutting-edge or "frontier" AI foundation models is that an adversary may use the models for preparing chemical, biological, radiological, nuclear, (CBRN), cyber, or other attacks. At least two methods can identify foundation…

Cryptography and Security · Computer Science 2024-05-21 Anthony M. Barrett , Krystal Jackson , Evan R. Murphy , Nada Madkour , Jessica Newman

The use of AI technologies is being integrated into the secure development of software-based systems, with an increasing trend of composing AI-based subsystems (with uncertain levels of performance) into automated pipelines. This presents a…

Software Engineering · Computer Science 2025-07-18 Emanuele Mezzi , Aurora Papotti , Fabio Massacci , Katja Tuma

Safety alignment can make frontier LMs overly conservative, degrading collaboration via hedging or false refusals. We present a lightweight toolkit with three parts: (1) Victor Calibration (VC), a multi-pass protocol that elicits a scalar…

Software Engineering · Computer Science 2025-12-30 Victor Stasiuc

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Artificial Intelligence · Computer Science 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

This position paper contends that modern AI research must adopt an antifragile perspective on safety -- one in which the system's capacity to guarantee long-term AI safety such as handling rare or out-of-distribution (OOD) events expands…

Artificial Intelligence · Computer Science 2025-09-18 Ming Jin , Hyunin Lee

Illusions of causality occur when people develop the belief that there is a causal connection between two variables with no supporting evidence. This cognitive bias has been proposed to underlie many societal problems including social…

Artificial Intelligence · Computer Science 2024-10-16 María Victoria Carro , Francisca Gauna Selasco , Denise Alejandra Mester , Mario Alejandro Leiva

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Cryptography and Security · Computer Science 2026-05-19 Tsafac Nkombong Regine Cyrille , Franziska Schwarz

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Computation and Language · Computer Science 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda
‹ Prev 1 8 9 10 Next ›