Related papers: The Evaluation Differential: When Frontier AI Mode…
We present EDGE, a general-purpose, misconception-aware adaptive learning framework composed of four stages: Evaluate (ability and state estimation), Diagnose (posterior infer-ence of misconceptions), Generate (counterfactual item…
Advancements in deep learning techniques have given a boost to the performance of anomaly detection. However, real-world and safety-critical applications demand a level of transparency and reasoning beyond accuracy. The task of anomaly…
Electroencephalography (EEG)-based emotion recognition suffers from severe performance degradation when models are transferred across heterogeneous datasets due to physiological variability, experimental paradigm differences, and device…
Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…
Violations of the parallel trends assumption pose significant challenges for causal inference in difference-in-differences (DiD) studies, especially in policy evaluations where pre-treatment dynamics and external shocks may bias estimates.…
Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often…
Capturing interactions among event arguments is an essential step towards robust event argument extraction (EAE). However, existing efforts in this direction suffer from two limitations: 1) The argument role type information of contextual…
For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the…
Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and…
AI evaluations are an important component of the AI governance toolkit, underlying current approaches to safety cases for preventing catastrophic risks. Our paper examines what these evaluations can and cannot tell us. Evaluations can…
Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the…
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…
The success of deep neural networks (DNNs) has promoted the widespread applications of person re-identification (ReID). However, ReID systems inherit the vulnerability of DNNs to malicious attacks of visually inconspicuous adversarial…
Content moderation systems are typically evaluated by measuring agreement with human labels. In rule-governed environments this assumption fails: multiple decisions may be logically consistent with the governing policy, and agreement…
Event argument extraction (EAE) aims to extract arguments with given roles from texts, which have been widely studied in natural language processing. Most previous works have achieved good performance in specific EAE datasets with dedicated…
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…
Evaluating the safety of frontier AI systems is an increasingly important concern, helping to measure the capabilities of such models and identify risks before deployment. However, it has been recognised that if AI agents are aware that…
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…
There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target object classifiers. Inspired by the observation that humans…
The safety of mental health AI is often judged at the wrong temporal scale. Current evaluations typically score isolated responses, endpoint outcomes, or aggregate dialogue quality, while clinically consequential failures may arise from the…