activity
20242026
collaborators

7 papers

cs.LG2026

TERC: A Transfer Entropy Redundancy Criterion for State Variable Selection in Reinforcement Learning

Charles Westphal, Stephen Hailes, Mirco Musolesi

Identifying the most suitable variables to represent the state is a fundamental challenge in Reinforcement Learning (RL). These variables must efficiently capture the information n…

cs.CR2026

Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

Charles Westphal, Timothy Douglas, Keivan Navaie +2

Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to d…

cs.CR2026

Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models

Charles Westphal, Keivan Navaie, Fernando E. Rosas

Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on trivially recoverable encodings. We f…

cs.LG2026

A Generalized Information Bottleneck Theory of Deep Learning

Charles Westphal, Stephen Hailes, Mirco Musolesi

The Information Bottleneck (IB) principle offers a compelling theoretical framework to understand how neural networks (NNs) learn. However, its practical utility has been constrain…

cs.LG2025

Partial Information Decomposition for Data Interpretability and Feature Selection

Charles Westphal, Stephen Hailes, Mirco Musolesi

In this paper, we introduce Partial Information Decomposition of Features (PIDF), a new paradigm for simultaneous data interpretability and feature selection. Contrary to tradition…

cs.LG2025

Mutual Information Preserving Neural Network Pruning

Charles Westphal, Stephen Hailes, Mirco Musolesi

Pruning has emerged as the primary approach used to limit the resource requirements of large neural networks (NNs). Since the proposal of the lottery ticket hypothesis, researchers…