Tag: ai-security
-
AI is driving CVE discover up, but exploits not exactly exploding
Of 1,061 vulnerabilities credited to AI-assisted discovery, 14 – 1.3% – have been exploited in the wild, which is the same rate as every other vulnerability. AI is multiplying the number of CVEs, not the danger of each one, and right now that hands defenders more to fix before attackers get there. Summarized by AI.…
-
Those rascally AIs: maybe there just weren’t any security controls.
AI alignment isn’t really the problem here: labs just need better infrastructure. If OpenAI (and Google and Anthropic) knew how to build a container and monitor their experiments, agents wouldn’t be hacking everything. And, By George, we _do know how_to make sandboxes that work, so the AI labs need to up their game and build…
You must be logged in to post a comment.