Related papers: Retrying vs Resampling in AI Control
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…
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…
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…
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…
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.…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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,…
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…