English
Related papers

Related papers: Auditing Games for Sandbagging

200 papers

Monumental advancements in artificial intelligence (AI) have lured the interest of doctors, lenders, judges, and other professionals. While these high-stakes decision-makers are optimistic about the technology, those familiar with AI…

Artificial Intelligence · Computer Science 2023-04-13 Zachariah Carmichael , Walter J Scheirer

This paper develops automated testing and debugging techniques for answer set solver development. We describe a flexible grammar-based black-box ASP fuzz testing tool which is able to reveal various defects such as unsound and incomplete…

Artificial Intelligence · Computer Science 2010-07-20 Robert Brummayer , Matti Järvisalo

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…

Machine Learning · Computer Science 2022-06-03 Aparna Balagopalan , Haoran Zhang , Kimia Hamidieh , Thomas Hartvigsen , Frank Rudzicz , Marzyeh Ghassemi

Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…

Computation and Language · Computer Science 2023-01-18 Lei Sha , Oana-Maria Camburu , Thomas Lukasiewicz

Our ability to know when to trust the decisions made by machine learning systems has not kept up with the staggering improvements in their performance, limiting their applicability in high-stakes domains. We introduce Prover-Verifier Games…

Machine Learning · Computer Science 2021-08-30 Cem Anil , Guodong Zhang , Yuhuai Wu , Roger Grosse

This position paper argues that job exposure to AI should be measured with grounded, evidence-based methods, not inferred from LLM priors alone. Current theoretical exposure measures use zero-shot prompting to classify task-level AI…

Information Retrieval · Computer Science 2026-05-18 Luca Mouchel , Pierre Bouquet , Yossi Sheffi

Given a learning problem with real-world tradeoffs, which cost function should the model be trained to optimize? This is the metric selection problem in machine learning. Despite its practical interest, there is limited formal guidance on…

Machine Learning · Statistics 2022-08-22 Gaurush Hiranandani

How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI. We analyse two algorithms for mitigating deception: The first is based on the path-specific objectives framework where paths in the…

Artificial Intelligence · Computer Science 2023-06-27 Ismail Sahbane , Francis Rhys Ward , C Henrik Åslund

The deployment of large-scale generative models is often restricted by their potential risk of causing harm to users in unpredictable ways. We focus on the problem of black-box red teaming, where a red team generates test cases and…

Artificial Intelligence · Computer Science 2023-05-30 Deokjae Lee , JunYeong Lee , Jung-Woo Ha , Jin-Hwa Kim , Sang-Woo Lee , Hwaran Lee , Hyun Oh Song

Group fairness metrics can detect when a deep learning model behaves differently for advantaged and disadvantaged groups, but even models that score well on these metrics can make blatantly unfair predictions. We present smooth prediction…

Machine Learning · Computer Science 2020-12-02 Ivoline C. Ngong , Krystal Maughan , Joseph P. Near

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

Recent advances in artificial intelligence have been strongly driven by the use of game environments for training and evaluating agents. Games are often accessible and versatile, with well-defined state-transitions and goals allowing for…

Machine Learning · Computer Science 2019-09-19 Benjamin Beyret , José Hernández-Orallo , Lucy Cheke , Marta Halina , Murray Shanahan , Matthew Crosby

Reliability in cloud AI infrastructure is crucial for cloud service providers, prompting the widespread use of hardware redundancies. However, these redundancies can inadvertently lead to hidden degradation, so called "gray failure", for AI…

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…

Artificial Intelligence · Computer Science 2026-05-12 Pedro Conde , Henrique Branquinho , Valerio Mazzone , Bruno Mendes , André Baptista , Nuno Moniz

Fuzzing has proven to be a highly effective approach to uncover software bugs over the past decade. After AFL popularized the groundbreaking concept of lightweight coverage feedback, the field of fuzzing has seen a vast amount of scientific…

AI-generated text detectors have recently gained adoption in educational and professional contexts. Prior research has uncovered isolated cases of bias, particularly against English Language Learners (ELLs) however, there is a lack of…

Artificial Intelligence · Computer Science 2025-12-15 Priyam Basu , Yunfeng Zhang , Vipul Raheja

Context: Issue tracking systems are used to track and describe tasks in the development process, e.g., requested feature improvements or reported bugs. However, past research has shown that the reported issue types often do not match the…

Software Engineering · Computer Science 2021-10-11 Steffen Herbold , Alexander Trautsch , Fabian Trautsch

As AI systems become more capable of complex agentic tasks, they also become more capable of pursuing undesirable objectives and causing harm. Previous work has attempted to catch these unsafe instances by interrogating models directly…

Artificial Intelligence · Computer Science 2026-03-24 Chloe Li , Mary Phuong , Daniel Tan

As Artificial Intelligence (AI) is increasingly used in areas that significantly impact human lives, concerns about fairness and transparency have grown, especially regarding their impact on protected groups. Recently, the intersection of…

Artificial Intelligence · Computer Science 2025-05-05 Vasiliki Papanikou , Danae Pla Karidi , Evaggelia Pitoura , Emmanouil Panagiotou , Eirini Ntoutsi

As large language models (LLMs) are increasingly used for code generation, concerns over the security risks have grown substantially. Early research has primarily focused on red teaming, which aims to uncover and evaluate vulnerabilities…

Software Engineering · Computer Science 2025-10-22 Chengquan Guo , Yuzhou Nie , Chulin Xie , Zinan Lin , Wenbo Guo , Bo Li