collaborators

10 papers

cs.LG2026

Detecting Neural Network Failures through Spectral Analysis of Internal Activations

Arunan J

Neural network misclassifications exhibit characteristic spectral instability in internal activations that is invisible at the output layer. This phenomenon is identified and forma…

cs.LG2026

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

Shijie Liu, Andrew C. Cullen, Paul Montague +2

The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even wri…

cs.LG2026

TRACER: Persistent Regularization for Robust Multimodal Finetuning

Hesam Asadollahzadeh, Feng Liu, Christopher Leckie +1

Mainstream strategies for finetuning pretrained multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastrophic forgetting. In this paper,…

cs.LG2026

Mechanistic Anomaly Detection via Functional Attribution

Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani

We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produced by normal or anomalous int…

cs.LG2026

Fortifying Time Series: DTW-Certified Robust Anomaly Detection

Shijie Liu, Tansu Alpcan, Christopher Leckie +1

Time-series anomaly detection is critical for ensuring safety in high-stakes applications, where robustness is a fundamental requirement rather than a mere performance metric. Addr…

cs.LG2025

On the Bayes Inconsistency of Disagreement Discrepancy Surrogates

Neil G. Marchant, Andrew C. Cullen, Feng Liu +1

Deep neural networks often fail when deployed in real-world contexts due to distribution shift, a critical barrier to building safe and reliable systems. An emerging approach to ad…