5 citations · 8 across the 5 of their papers we have counts for
6 papers
Seven simple steps for log analysis in AI systems
Magda Dubois, Ekin Zorer, Maia Hamin +17
AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess…
A Multi-Turn Framework for Evaluating AI Misuse in Fraud and Cybercrime Scenarios
Kimberly T. Mai, Anna Gausen, Magda Dubois +5
AI is increasingly being used to assist fraud and cybercrime. However, it is unclear the extent to which current large language models can provide useful information for complex cr…
SoK: Data Minimization in Machine Learning
Robin Staab, Nikola Jovanović, Kimberly Mai +4
Data minimization (DM) describes the principle of collecting only the data strictly necessary for a given task. It is a foundational principle across major data protection regulati…
An Example Safety Case for Safeguards Against Misuse
Joshua Clymer, Jonah Weinbaum, Robert Kirk +3
Existing evaluations of AI misuse safeguards provide a patchwork of evidence that is often difficult to connect to real-world decisions. To bridge this gap, we describe an end-to-e…
Self-Supervised Losses for One-Class Textual Anomaly Detection
Kimberly T. Mai, Toby Davies, Lewis D. Griffin
Current deep learning methods for anomaly detection in text rely on supervisory signals in inliers that may be unobtainable or bespoke architectures that are difficult to tune. We…
Brittle Features May Help Anomaly Detection
Kimberly T. Mai, Toby Davies, Lewis D. Griffin
One-class anomaly detection is challenging. A representation that clearly distinguishes anomalies from normal data is ideal, but arriving at this representation is difficult since…