Assume Breach When Building AI Apps
AI jailbreaks are not vulnerabilities; they are expected behavior.
You May Also Enjoy
Reconstructing a timeline for Amazon Q prompt infection
In the 404media article the hacker explains how they did it:
Why Aren’t We Making Any Progress In Security From AI
Guardrails Are Soft Boundaries. Hard Boundaries Do Exist.
OAI Q&A on Security From AI
This is part 3 on OpenAI’s Security Research Conference. Here are part 1 and part 2.
Fully-Autonomous AI Systems Are Discovering Vulns Today
This is part 2 on OpenAI’s Security Research Conference. Here is part 1.