15 citations · 47 across the 26 of their papers we have counts for
27 papers
Referential Security as a New Paradigm for AI Evaluations
Dan Ristea, Vasilios Mavroudis
Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously…
International AI Safety Report 2026
Yoshua Bengio, Stephen Clare, Carina Prunkl +89
The International AI Safety Report 2026 synthesises the current scientific evidence on the capabilities, emerging risks, and safety of general-purpose AI systems. The report series…
The science and practice of proportionality in AI risk evaluations
Carlos Mougan, Lauritz Morlock, Jair Aguirre +19
A global challenge in artificial intelligence (AI) regulation lies in achieving effective risk management without compromising innovation and technical progress. The European Union…
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies
Miles Brundage, Noemi Dreksler, Aidan Homewood +45
We outline a vision for frontier AI auditing, which we define as rigorous third-party verification of frontier AI developers' safety and security claims, and evaluation of their sy…
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…
Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse
Steve Barrett, Malcolm Murray, Otter Quarks +17
Advanced AI systems offer substantial benefits but also introduce risks. In 2025, AI-enabled cyber offense has emerged as a concrete example. This technical report applies a quanti…
International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications
Yoshua Bengio, Stephen Clare, Carina Prunkl +70
Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to re…
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…
Analysis of Publicly Accessible Operational Technology and Associated Risks
Matthew Rodda, Vasilios Mavroudis
Operational Technology (OT) is an integral component of critical national infrastructure, enabling automation and control in industries such as energy, manufacturing, and transport…
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…
Quantifying Mix Network Privacy Erosion with Generative Models
Vasilios Mavroudis, Tariq Elahi
Modern mix networks improve over Tor and provide stronger privacy guarantees by robustly obfuscating metadata. As long as a message is routed through at least one honest mixnode, t…
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…
Guidelines for Applying RL and MARL in Cybersecurity Applications
Vasilios Mavroudis, Gregory Palmer, Sara Farmer +6
Reinforcement Learning (RL) and Multi-Agent Reinforcement Learning (MARL) have emerged as promising methodologies for addressing challenges in automated cyber defence (ACD). These…
International AI Safety Report
Yoshua Bengio, Sören Mindermann, Daniel Privitera +93
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…
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…
International Scientific Report on the Safety of Advanced AI (Interim Report)
Yoshua Bengio, Sören Mindermann, Daniel Privitera +41
This is the interim publication of the first International Scientific Report on the Safety of Advanced AI. The report synthesises the scientific understanding of general-purpose AI…