English
Related papers

Related papers: Retrying vs Resampling in AI Control

200 papers

Randomized controlled trials (RCTs) are indispensable for establishing the clinical value of medical artificial-intelligence (AI) tools, yet their high cost and long timelines hinder timely validation as new models emerge rapidly. Here, we…

Machine Learning · Computer Science 2025-11-17 Michael Nercessian , Wenxin Zhang , Alexander Schubert , Daphne Yang , Maggie Chung , Ahmed Alaa , Adam Yala

This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when…

Artificial Intelligence · Computer Science 2026-04-02 Alexandra Souly , Robert Kirk , Jacob Merizian , Abby D'Cruz , Xander Davies

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Cryptography and Security · Computer Science 2021-01-21 Ximing Qiao , Yuhua Bai , Siping Hu , Ang Li , Yiran Chen , Hai Li

Online platforms routinely compare multi-armed bandit algorithms, such as UCB and Thompson Sampling, to select the best-performing policy. Unlike standard A/B tests for static treatments, each run of a bandit algorithm over $T$ users…

Machine Learning · Computer Science 2026-04-14 Huiling Meng , Ningyuan Chen , Xuefeng Gao

Safely controlling unknown dynamical systems is one of the biggest challenges in the field of control. Oftentimes, an approximate model of a system's dynamics exists which provides beneficial information for the selection of controls.…

Systems and Control · Electrical Eng. & Systems 2023-08-10 Ethan Lau , Vaibhav Srivastava , Shaunak D. Bopardikar

Existing research on generative AI security is primarily driven by mutually reinforcing attack and defense methodologies grounded in empirical experience. This dynamic frequently gives rise to previously unknown attacks that can circumvent…

Cryptography and Security · Computer Science 2026-01-01 Yu Cui , Hang Fu , Sicheng Pan , Zhuoyu Sun , Yifei Liu , Yuhong Nie , Bo Ran , Baohan Huang , Xufeng Zhang , Haibin Zhang , Cong Zuo , Licheng Wang

Sketching enables many exciting applications, notably, image retrieval. The fear-to-sketch problem (i.e., "I can't sketch") has however proven to be fatal for its widespread adoption. This paper tackles this "fear" head on, and for the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Ayan Kumar Bhunia , Subhadeep Koley , Abdullah Faiz Ur Rahman Khilji , Aneeshan Sain , Pinaki Nath Chowdhury , Tao Xiang , Yi-Zhe Song

Scoring models support decision-making in financial institutions. Their estimation and evaluation are based on the data of previously accepted applicants with known repayment behavior. This creates sampling bias: the available labeled data…

Code review is central to software engineering education but hard to scale in capstone projects due to tight deadlines, uneven peer feedback, and limited prior experience. We investigate an LLM-as-reviewer integrated directly into GitHub…

Software Engineering · Computer Science 2026-04-28 Eduardo Oliveira , Michael Fu , Patanamon Thongtanunam , Sonsoles López-Pernas , Mohammed Saqr

In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of…

Artificial Intelligence · Computer Science 2021-05-17 Jens Braband , Hendrik Schäbe

A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria. We contribute to this effort with a comparative perspective in this study. Our comparison of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-15 Xin Wang , Junich Yamagishi

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling, Reprompting infers the CoT recipes that work…

Machine Learning · Computer Science 2024-05-27 Weijia Xu , Andrzej Banburski-Fahey , Nebojsa Jojic

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Artificial Intelligence · Computer Science 2026-02-17 Igor Santos-Grueiro

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…

Computer Science and Game Theory · Computer Science 2016-11-29 Bo Li , Yevgeniy Vorobeychik , Xinyun Chen

The effectiveness of machine learning models, particularly in unbalanced classification tasks, is often hindered by the failure to differentiate between critical instances near the decision boundary and redundant samples concentrated in the…

Machine Learning · Computer Science 2025-09-25 Samir Brahim Belhaouari , Yunis Carreon Kahalan , Humaira Shaffique , Ismael Belhaouari , Ashhadul Islam

Retrieval-Augmented Code Generation (RACG) is increasingly adopted to enhance Large Language Models for software development, yet its security implications remain dangerously underexplored. This paper conducts the first systematic…

Cryptography and Security · Computer Science 2025-12-29 Tian Li , Bo Lin , Shangwen Wang , Yusong Tan

Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and…

Artificial Intelligence · Computer Science 2026-05-01 Yu-Chao Huang , Zhen Tan , Mohan Zhang , Pingzhi Li , Zhuo Zhang , Tianlong Chen

While artificial intelligence (AI) is advancing rapidly and mastering increasingly complex problems with astonishing performance, the safety assurance of such systems is a major concern. Particularly in the context of safety-critical,…

Artificial Intelligence · Computer Science 2025-07-01 Lars Ullrich , Walter Zimmer , Ross Greer , Knut Graichen , Alois C. Knoll , Mohan Trivedi

Plagiarism in programming assignments is a persistent issue in computer science education, increasingly complicated by the emergence of automated obfuscation attacks. While software plagiarism detectors are widely used to identify…

Software Engineering · Computer Science 2025-05-27 Timur Sağlam , Larissa Schmid