activity
20212026
most citedSelf-Supervised Losses for One-Class Textual Anomaly Detection

5 citations · 8 across the 5 of their papers we have counts for

collaborators

6 papers

cs.AI20261 cited

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…

cs.CY20261 cited

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…

cs.LG2025

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…

cs.LG2025

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…

cs.CL20225 cited

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…

cs.LG20211 cited

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…