William Hackett

Founding Machine Learning Engineer

William Hackett is an Artificial Intelligence & Security researcher PhD who studied at Lancaster University. William excels in the understanding and practical applications of AI and computing. William develops state-of-the-art security solutions for AI models, uncovering fundamental insights behind AI attacks and ways to make models more secure.

Author's Work

Outsmarting AI Guardrails with Invisible Characters and Adversarial Prompts

This blog summarizes the key findings from our research paper, Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails (2025). For the first time, we present an empirical analysis of character injection and adversarial machine learning (AML) evasion attacks across multiple commercial and open-source guardrails.

Don’t Think too Deep on the Matter: Studying DeepSeek-R1’s Susceptibility to Exhaustion Attacks

Through our testing we found that DeepSeek-R1 proved highly susceptible to resource exhaustion attacks, specifically LLM10:2025 Unbounded Consumption from the OWASP LLM Top 10, which forced the model to engage in prolonged reasoning, significantly increasing its response time.

Bypassing AI-Driven Deepfake Detection via Evasion Attacks

Discover how evasion attacks are bypassing AI-driven deepfake detection, posing significant risks to cybersecurity. Learn about defense strategies and the importance of red teaming for AI security.

Bypassing Azure AI Content Safety Guardrails

Discover a security issue within Azure AI Content Safety guardrails that Mindgard has discovered and reported to Microsoft.