47 citations · 134 across the 37 of their papers we have counts for
39 papers
REPLICANT: Learning Policies for Evading and Hardening Malware Detectors
Shae McFadden, Ilias Tsingenopoulos, Mario D'Onghia +5
To determine the real-world effectiveness of machine learning based malware detection, it is vital to evaluate its robustness against highly capable adversaries. However, state-of-…
Proving the Utility of Large Language Models in Cybersecurity Simulations: A Comprehensive Examination
Stylianos Kampakis, Fabio Rovai, Marcos Charalambides +2
Cyber threats continue to escalate in both frequency and sophistication, necessitating more adaptive and scalable defense strategies. This paper explores how Large Language Models…
Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
Sahar Abdelnabi, Chris Hicks, Konrad Rieck +1
The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges th…
Building Better Environments for Autonomous Cyber Defence
Chris Hicks, Elizabeth Bates, Shae McFadden +12
In November 2025, the authors ran a workshop on the topic of what makes a good reinforcement learning (RL) environment for autonomous cyber defence (ACD). This paper details the kn…
On The Effectiveness of the UK NIS Regulations as a Mandatory Cybersecurity Reporting Regime
Junade Ali, Chris Hicks
Existing cybersecurity literature lacks a source of empirical, representative data as to the true nature of cyberattacks on Critical National Infrastructure. We have obtained UK-wi…
SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
Shae McFadden, Myles Foley, Elizabeth Bates +5
Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, tr…
Beyond Rewards in Reinforcement Learning for Cyber Defence
Elizabeth Bates, Chris Hicks, Vasilios Mavroudis
Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically…
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
Alexandra Souly, Javier Rando, Ed Chapman +10
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…
What if we could hot swap our Biometrics?
Jon Crowcroft, Anil Madhavapeddy, Chris Hicks +2
What if you could really revoke your actual biometric identity, and install a new one, by live rewriting your biological self? We propose some novel mechanisms for hot swapping ide…
DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
Shae McFadden, Myles Foley, Mario D'Onghia +4
Malware detection in real-world settings must deal with evolving threats, limited labeling budgets, and uncertain predictions. Traditional classifiers, without additional mechanism…
Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning
Sanyam Vyas, Alberto Caron, Chris Hicks +2
Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored. This work investigates backdoor…
On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
Alberto Caron, Chris Hicks, Vasilios Mavroudis
In this work, we address the challenge of data-efficient exploration in reinforcement learning by examining existing principled, information-theoretic approaches to intrinsic motiv…
From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs
Alsharif Abuadbba, Chris Hicks, Kristen Moore +4
Large Language Models (LLMs) are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simula…
One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image
Ezzeldin Shereen, Dan Ristea, Shae McFadden +3
Retrieval-augmented generation (RAG) is instrumental for inhibiting hallucinations in large language models (LLMs) through the use of a factual knowledge base (KB). Although PDF do…
Towards Causal Model-Based Policy Optimization
Alberto Caron, Vasilios Mavroudis, Chris Hicks
Real-world decision-making problems are often marked by complex, uncertain dynamics that can shift or break under changing conditions. Traditional Model-Based Reinforcement Learnin…
Less is more? Rewards in RL for Cyber Defence
Elizabeth Bates, Chris Hicks, Vasilios Mavroudis
The last few years have seen an explosion of interest in autonomous cyber defence agents based on deep reinforcement learning. Such agents are typically trained in a cyber gym envi…
An Attentive Graph Agent for Topology-Adaptive Cyber Defence
Ilya Orson Sandoval, Isaac Symes Thompson, Vasilios Mavroudis +1
As cyber threats grow increasingly sophisticated, reinforcement learning (RL) is emerging as a promising technique to create intelligent and adaptive cyber defense systems. However…
Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points
Dan Ristea, Shae McFadden, Ezzeldin Shereen +4
Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, especially as agentic coding frameworks inc…
Inherently Interpretable and Uncertainty-Aware Models for Online Learning in Cyber-Security Problems
Benjamin Kolicic, Alberto Caron, Chris Hicks +1
In this paper, we address the critical need for interpretable and uncertainty-aware machine learning models in the context of online learning for high-risk industries, particularly…
Fairness with Exponential Weights
Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
Motivated by the need to remove discrimination in certain applications, we develop a meta-algorithm that can convert any efficient implementation of an instance of Hedge (or equiva…
CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents
Harry Emerson, Liz Bates, Chris Hicks +1
CybORG++ is an advanced toolkit for reinforcement learning research focused on network defence. Building on the CAGE 2 CybORG environment, it introduces key improvements, including…
HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation
Dan Ristea, Vasilios Mavroudis
We introduce HonestCyberEval, a new benchmark for assessing AI models' capabilities and risks in automated software exploitation, focusing on their ability to detect and exploit vu…
Entity-based Reinforcement Learning for Autonomous Cyber Defence
Isaac Symes Thompson, Alberto Caron, Chris Hicks +1
A significant challenge for autonomous cyber defence is ensuring a defensive agent's ability to generalise across diverse network topologies and configurations. This capability is…
Autonomous Network Defence using Reinforcement Learning
Myles Foley, Chris Hicks, Kate Highnam +1
In the network security arms race, the defender is significantly disadvantaged as they need to successfully detect and counter every malicious attack. In contrast, the attacker nee…