504 citations · 656 across the 9 of their papers we have counts for
10 papers
BRANCH: Bypassing Multi-Scanner AI Guardrails
William Hackett, Peter Garraghan
AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks. Guardrails monitor and validate mod…
Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring
William Hackett, Peter Garraghan
As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical. Guardrail systems that detect an…
Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems
William Hackett, Lewis Birch, Stefan Trawicki +2
Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We dem…
Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization
Stefan Trawicki, William Hackett, Lewis Birch +2
Adversarial Machine Learning (AML) is a rapidly growing field of security research, with an often overlooked area being model attacks through side-channels. Previous works show suc…
Model Leeching: An Extraction Attack Targeting LLMs
Lewis Birch, William Hackett, Stefan Trawicki +2
Model Leeching is a novel extraction attack targeting Large Language Models (LLMs), capable of distilling task-specific knowledge from a target LLM into a reduced parameter model.…
PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models
William Hackett, Stefan Trawicki, Zhengxin Yu +2
Adversarial extraction attacks constitute an insidious threat against Deep Learning (DL) models in-which an adversary aims to steal the architecture, parameters, and hyper-paramete…