Tom Bonner
tbo.bsky.social
Tom Bonner
@tbo.bsky.social
SVP of Research @hiddenlayer.bsky.social.

Formerly Norman, HP, Cylance, BlackBerry. All views are my own.
Announcing our latest attack technique, "Policy Puppetry" - a single, transferable prompt blending structured policy & roleplay that bypasses alignment in frontier AI models. Game-changing for red-teaming!

#AI #GenAI #RedTeam #CyberSecurity

hiddenlayer.com/innovation-h...
Novel Universal Bypass for All Major LLMs
HiddenLayer’s latest research uncovers a universal prompt injection bypass impacting GPT-4, Claude, Gemini, and more, exposing major LLM security gaps.
hiddenlayer.com
April 24, 2025 at 2:41 PM
Our researchers discovered that the Hugging Face PyTorch to Safetensors conversion service could easily be compromised by attackers, who could tamper with models and leak the token used to create pull requests from the official bot.

hiddenlayer.com/research/sil...
Silent Sabotage | HiddenLayer Research
In this blog, we show how an attacker could compromise the Hugging Face Safetensors conversion space and its associated service bot.
hiddenlayer.com
February 21, 2024 at 4:01 PM
Some great work by the team, finding 6 CVEs in ClearML and uncovering a complete attack chain that can be exploited to deploy payloads to end-users.

hiddenlayer.com/research/not...
February 7, 2024 at 4:26 PM