English
Related papers

Related papers: Fundamental Limits of Black-Box Safety Evaluation:…

200 papers

Autonomous vehicles are advanced driving systems that are well known to be vulnerable to various adversarial attacks, compromising vehicle safety and posing a risk to other road users. Rather than actively training complex adversaries by…

Artificial Intelligence · Computer Science 2024-01-02 Aizaz Sharif , Dusica Marijan

Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment to ensure their reliability and safety. However, accurate world models often have high computational…

Artificial Intelligence · Computer Science 2025-04-08 Fernando Rosas , Alexander Boyd , Manuel Baltieri

Many safety failures in machine learning arise when models are used to assign predictions to people (often in settings like lending, hiring, or content moderation) without accounting for how individuals can change their inputs. In this…

Machine Learning · Computer Science 2025-07-04 Seung Hyun Cheon , Meredith Stewart , Bogdan Kulynych , Tsui-Wei Weng , Berk Ustun

With the growing interest in deploying robots in unstructured and uncertain environments, there has been increasing interest in factoring risk into safety-critical control development. Similarly, the authors believe risk should also be…

Systems and Control · Electrical Eng. & Systems 2022-03-08 Prithvi Akella , Mohamadreza Ahmadi , Aaron D. Ames

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

Recent developments in Artificial Intelligence (AI) and their applications in critical industries such as healthcare, fin-tech and cybersecurity have led to a surge in research in explainability in AI. Innovative research methods are being…

Artificial Intelligence · Computer Science 2025-08-26 Aoun E Muhammad , Kin-Choong Yow , Nebojsa Bacanin-Dzakula , Muhammad Attique Khan

The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Hang-Cheng Dong , Yuhao Jiang , Yibo Jiao , Lu Zou , Kai Zheng , Bingguo Liu , Dong Ye , Guodong Liu

Automated Driving Systems (ADS), including Advanced Driver Assistance Systems (ADAS), must fulfill not only high functional expectations but also stringent timing constraints mandated by international regulations and standards. Regulatory…

Software Engineering · Computer Science 2026-05-05 Sebastian Dingler , Philip Rehkop , Florian Mayer , Ralf Muenzenberger

We consider the problem of evaluating black-box multi-class classifiers. In the standard setup, we observe class labels $Y\in \{0,1,\ldots,M-1\}$ generated according to the conditional distribution $ Y|X \sim \text{…

Methodology · Statistics 2026-04-08 Yuchen Chen , Jing Lei

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed…

Machine Learning · Computer Science 2019-08-02 Alessio Russo , Alexandre Proutiere

Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner must optimize a task objective using only feasibility samples from a black-box Simulator,…

Systems and Control · Electrical Eng. & Systems 2026-04-22 Tongxin Li

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

Trajectory prediction systems are critical for autonomous vehicle safety, yet remain vulnerable to adversarial attacks that can cause catastrophic traffic behavior misinterpretations. Existing attack methods require white-box access with…

Robotics · Computer Science 2026-03-30 Jiaxiang Li , Jun Yan , Daniel Watzenig , Huilin Yin

Black-box optimization is increasingly used in engineering design problems where simulation-based evaluations are costly and gradients are unavailable. In this context, the optimization community has largely analyzed algorithm performance…

Neural and Evolutionary Computing · Computer Science 2026-02-06 Iván Olarte Rodríguez , Gokhan Serhat , Mariusz Bujny , Fabian Duddeck , Thomas Bäck , Elena Raponi

Black-box transformations have been extensively studied in algorithmic mechanism design as a generic tool for converting algorithms into truthful mechanisms without degrading the approximation guarantees. While such transformations have…

Computer Science and Game Theory · Computer Science 2019-08-16 Warut Suksompong

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…

Artificial Intelligence · Computer Science 2025-03-11 Dany Moshkovich , Hadar Mulian , Sergey Zeltyn , Natti Eder , Inna Skarbovsky , Roy Abitbol

AI incident reporting requirements are emerging in regulation and policy, yet no operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to international coordination. This paper…

Computers and Society · Computer Science 2026-05-20 Francesca Gomez , Matthew Ball , Michael Harre , Lydia Preston , Josephine Schwab , Caio Machado

Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of dataset misuse, this paper explores \textit{dataset…

Cryptography and Security · Computer Science 2025-12-09 Ruikai Zhou , Kang Yang , Xun Chen , Wendy Hui Wang , Guanhong Tao , Jun Xu

This paper examines the critical challenges and potential solutions for conducting secure and effective external evaluations of general-purpose AI (GPAI) models. With the exponential growth in size, capability, reach and accompanying risk…

Computers and Society · Computer Science 2025-03-14 Alejandro Tlaie , Jimmy Farrell

We study the problem of predictive runtime monitoring of black-box dynamical systems with quantitative safety properties. The black-box setting stipulates that the exact semantics of the dynamical system and the controller are unknown, and…

Systems and Control · Electrical Eng. & Systems 2024-12-24 Thomas A. Henzinger , Fabian Kresse , Kaushik Mallik , Emily Yu , Đorđe Žikelić