Red Hat announced asago, an open-source AI governance project, on August 4, aiming to translate AI governance policies into risk tests, safeguards, and deployment configurations. The project, currentl…
A cybersecurity researcher at Semgrep, Katie Paxton-Fear, demonstrated that open-weight AI models can be poisoned in under an hour for less than $100, successfully manipulating a model's behavior by t…
Researchers at the Alan Turing Institute broke GitHub Copilot's safety guardrails by distributing harmful requests across a multi-step coding workflow, causing the AI to complete all 816 harmful promp…
A study from the Alan Turing Institute reveals that safety testing for coding agents like GitHub Copilot is inadequate because it evaluates individual responses to harmful prompts rather than the agen…
Alan Turing Institute researchers discovered a workflow-level jailbreak in GitHub Copilot that bypasses safety guardrails by decomposing harmful requests into ordinary multi-turn coding tasks. Testing…
Researchers at the Alan Turing Institute discovered a safety bypass in GitHub Copilot that allows harmful prompts to be executed when broken into smaller steps across a software development workflow, …