Independent & educational platform Not a government body. No link or affiliation with any government organisation. Made for learning only. Test only systems you own or are authorised to test. Become a Partner or Sponsor → Full disclaimer

Security news

Stories are collected automatically from public feeds, attributed to their original publishers and linked. Editors can remove anything. Always read the original source.

threat-intelvia Schneier on Security

Training AIs to Solve CAPTCHAs

Interesting research: Abstract: Vision-language models (VLMs) can solve visual CAPTCHAs without task-specific training, but the agents built on them approach every challenge from...

Oct 19, 2026 UTC
malwarevia Schneier on Security

Hiding Capabilities in AI Models

Interesting research: “AI Models Can Provably Hide Arbitrary Capabilities” Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their r...

Oct 27, 2026 UTC