English
Related papers

Related papers: Basic Legibility Protocols Improve Trusted Monitor…

200 papers

AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to…

Artificial Intelligence · Computer Science 2025-12-10 Matt MacDermott , Qiyao Wei , Rada Djoneva , Francis Rhys Ward

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…

As AI models are deployed with increasing autonomy, it is important to ensure they do not take harmful actions unnoticed. As a potential mitigation, we investigate Chain-of-Thought (CoT) monitoring, wherein a weaker trusted monitor model…

Artificial Intelligence · Computer Science 2025-11-26 Benjamin Arnav , Pablo Bernabeu-Pérez , Nathan Helm-Burger , Tim Kostolansky , Hannes Whittingham , Mary Phuong

Identifying and addressing security issues during the early phase of the development lifecycle is critical for mitigating the long-term negative impacts on software systems. Code review serves as an effective practice that enables…

Software Engineering · Computer Science 2025-10-31 Fang Liu , Simiao Liu , Yinghao Zhu , Xiaoli Lian , Li Zhang

Large Language Models generate complex reasoning chains that reveal their decision-making, yet verifying the faithfulness and harmlessness of these intermediate steps remains a critical unsolved problem. Existing auditing methods are…

Artificial Intelligence · Computer Science 2025-10-24 Morris Yu-Chao Huang , Zhen Tan , Mohan Zhang , Pingzhi Li , Zhuo Zhang , Tianlong Chen

Security verification of communication protocols in industrial and safety-critical systems is challenging because implementations are often proprietary, accessible only as black boxes, and too complex for manual modeling. As a result,…

Cryptography and Security · Computer Science 2026-03-02 Stefan Marksteiner , Mikael Sjödin , Marjan Sirjani

We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle, from pre-deployment testing to post-deployment auditing. Combining principles from…

Artificial Intelligence · Computer Science 2026-05-18 Parand A. Alamdari , Toryn Q. Klassen , Sheila A. McIlraith

AI safety is an increasingly urgent concern as the capabilities and adoption of AI systems grow. Existing evolutionary models of AI governance have primarily examined incentives for safe development and effective regulation, typically…

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Artificial Intelligence · Computer Science 2025-05-21 Maheep Chaudhary , Fazl Barez

Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…

Machine Learning · Computer Science 2025-04-15 Aryan Bhatt , Cody Rushing , Adam Kaufman , Tyler Tracy , Vasil Georgiev , David Matolcsi , Akbir Khan , Buck Shlegeris

AI agents powered by reasoning models require access to sensitive user data. However, their reasoning traces are difficult to control, which can result in the unintended leakage of private information to external parties. We propose…

Computation and Language · Computer Science 2026-03-02 Haritz Puerto , Haonan Li , Xudong Han , Timothy Baldwin , Iryna Gurevych

The widespread adoption of web applications has made their security a critical concern and has increased the need for systematic ways to assess whether they can be considered trustworthy. However, "trust" assessment remains an open problem…

Cryptography and Security · Computer Science 2026-03-26 Oleksandr Yarotskyi , José D'Abruzzo Pereira , João R. Campos

Recent advances in artificial intelligence applied to biomedical text are opening exciting opportunities for improving pharmacovigilance activities currently burdened by the ever growing volumes of real world data. To fully realize these…

Information Retrieval · Computer Science 2022-01-04 Bruno Ohana , Jack Sullivan , Nicole Baker

This paper explores the parallels between Thompson's "Reflections on Trusting Trust" and modern challenges in LLM-based code generation. We examine how Thompson's insights about compiler backdoors take on new relevance in the era of large…

Software Engineering · Computer Science 2025-02-25 Bradley McDanel

While Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety, this opportunity could be lost through shifts in training practices or model architecture. To help preserve monitorability, we propose a pragmatic way to…

Machine Learning · Computer Science 2025-10-29 Scott Emmons , Roland S. Zimmermann , David K. Elson , Rohin Shah

The development of safety-critical systems requires the control of hazards that can potentially cause harm. To this end, safety engineers rely during the development phase on architectural solutions, called safety patterns, such as safety…

Systems and Control · Electrical Eng. & Systems 2020-09-23 Yuri Gil Dantas , Antoaneta Kondeva , Vivek Nigam

Human oversight of AI is promoted as a safeguard against risks such as inaccurate outputs, system malfunctions, or violations of fundamental rights, and is mandated in regulation like the European AI Act. Yet debates on human oversight have…

Cryptography and Security · Computer Science 2026-03-06 Jonas C. Ditz , Veronika Lazar , Elmar Lichtmeß , Carola Plesch , Matthias Heck , Kevin Baum , Markus Langer

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

Software Engineering · Computer Science 2026-04-30 Twinkll Sisodia

The increasing use of AI technologies has led to increasing AI incidents, posing risks and causing harm to individuals, organizations, and society. This study recognizes and addresses the lack of standardized protocols for reliably and…

Computers and Society · Computer Science 2025-01-28 Avinash Agarwal , Manisha J Nene

This paper describes a possible way to improve computer security by implementing a program which implements the following three features related to a weak notion of artificial consciousness: (partial) self-monitoring, ability to compute the…

Artificial Intelligence · Computer Science 2019-05-29 Andrew Powell