English
Related papers

Related papers: Stress-Testing Alignment Audits With Prompt-Level …

200 papers

The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them…

Machine Learning · Computer Science 2026-03-25 Chunxiao Li , Lijun Li , Jing Shao

Adversarial decision-making in partially observable multi-agent systems requires sophisticated strategies for both deception and counter-deception. This paper presents a sequential hypothesis testing (SHT)-driven framework that captures the…

Optimization and Control · Mathematics 2026-04-14 Haosheng Zhou , Daniel Ralston , Xu Yang , Ruimeng Hu

LLMs are increasingly embedded in everyday decision-making, yet their outputs can encode subtle, unintended behaviours that shape user beliefs and actions. We refer to these covert, goal-directed behaviours as hidden intentions, which may…

Computation and Language · Computer Science 2026-01-27 Devansh Srivastav , David Pape , Lea Schönherr

Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger…

Cryptography and Security · Computer Science 2026-04-10 Wenkui Yang , Chao Jin , Haisu Zhu , Weilin Luo , Derek Yuen , Kun Shao , Huaibo Huang , Junxian Duan , Jie Cao , Ran He

Structured data-quality issues, such as missing values correlated with demographics, culturally biased labels, or systemic selection biases, routinely degrade the reliability of machine-learning pipelines. Regulators now increasingly demand…

Machine Learning · Computer Science 2025-06-03 Jiongli Zhu , Geyang Xu , Felipe Lorenzi , Boris Glavic , Babak Salimi

Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…

Machine Learning · Computer Science 2025-10-07 Ege Cakar , Per Ola Kristensson

Search-based testing is widely used to find bugs in models of complex Cyber-Physical Systems. Latest research efforts have improved this approach by casting it as a falsification procedure of formally specified temporal properties,…

Logic in Computer Science · Computer Science 2017-10-03 Simone Silvetti , Alberto Policriti , Luca Bortolussi

Science and technology have a growing need for effective mechanisms that ensure reliable, controlled performance from black-box machine learning algorithms. These performance guarantees should ideally hold conditionally on the input-that is…

Machine Learning · Computer Science 2025-03-28 Vincent Blot , Anastasios N Angelopoulos , Michael I Jordan , Nicolas J-B Brunel

Standard safety alignment optimizes Large Language Models (LLMs) for universal helpfulness and honesty, effectively instilling a rigid "Boy Scout" morality. While robust for general-purpose assistants, this one-size-fits-all ethical…

Artificial Intelligence · Computer Science 2026-01-12 Cooper Lin , Maohao Ran , Yanting Zhang , Zhenglin Wan , Hongwei Fan , Yibo Xu , Yike Guo , Wei Xue , Jun Song

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

Computation and Language · Computer Science 2026-05-19 Nivya Talokar , Ayush K Tarun , Murari Mandal , Maksym Andriushchenko , Antoine Bosselut

Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning exposes payment systems to prompt-driven manipulation. The Agent Payments Protocol (AP2) aims to…

Cryptography and Security · Computer Science 2026-05-20 Tanusree Debi , Wentian Zhu , Pranjol Sen Gupta

We consider the issue of strategic behaviour in various peer-assessment tasks, including peer grading of exams or homeworks and peer review in hiring or promotions. When a peer-assessment task is competitive (e.g., when students are graded…

Multiagent Systems · Computer Science 2020-10-09 Ivan Stelmakh , Nihar B. Shah , Aarti Singh

Large language model (LLM) agents increasingly rely on skills to package reusable capabilities through instructions, tools, and resources. High-quality skills embed expert knowledge, curated workflows, and execution constraints into agents,…

Cryptography and Security · Computer Science 2026-04-28 Zihan Wang , Rui Zhang , Yu Liu , Chi Liu , Qingchuan Zhao , Hongwei Li , Guowen Xu

System prompt configuration can make the difference between near-total phishing blindness and near-perfect detection in LLM email agents. We present PhishNChips, a study of 11 models under 10 prompt strategies, showing that prompt-model…

Cryptography and Security · Computer Science 2026-03-27 Ron Litvak

Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing processes, however, are labor-intensive and reliant on human expertise, posing challenges in maintaining…

Computation and Language · Computer Science 2024-10-11 Xu Yao , Xiaoxu Wu , Xi Li , Huan Xu , Chenlei Li , Ping Huang , Si Li , Xiaoning Ma , Jiulong Shan

Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly pursue misaligned goals. One approach to mitigating such…

Computation and Language · Computer Science 2026-03-03 Simon Storf , Rich Barton-Cooper , James Peters-Gill , Marius Hobbhahn

We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to possess specific knowledge that they apply downstream but…

Machine Learning · Computer Science 2025-11-03 Bartosz Cywiński , Emil Ryd , Rowan Wang , Senthooran Rajamanoharan , Neel Nanda , Arthur Conmy , Samuel Marks

Performance modeling typically relies on two antithetic methodologies: white box models, which exploit knowledge on system's internals and capture its dynamics using analytical approaches, and black box techniques, which infer relations…

Performance · Computer Science 2014-10-21 Diego Didona , Paolo Romano

We study the problem of auditing the fairness of a given classifier under partial feedback, where true labels are available only for positively classified individuals, (e.g., loan repayment outcomes are observed only for approved…

Machine Learning · Computer Science 2026-02-24 Nirjhar Das , Mohit Sharma , Praharsh Nanavati , Kirankumar Shiragur , Amit Deshpande

This work presents an attack-aware deepfake and image-forensics detector designed for robustness, well-calibrated probabilities, and transparent evidence under realistic deployment conditions. The method combines red-team training with…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Noor Fatima , Hasan Faraz Khan , Muzammil Behzad