LLM

Sovereign Shield 0.6.0 is live: an Inspect panel showing your prompt beside what the provider actually gets, plus API-key detection, custom terms and realistic stand-ins. Still entirely local.

• Sovereign Shield
• AI security
• privacy

Sovereign Shield's browser extension is live on the Chrome Web Store: it redacts Swiss, EU and international identifiers before your prompt reaches ChatGPT, Gemini or Claude.

• Sovereign Shield
• AI security
• privacy

A deterministic gateway that lets your team use Gemini or Claude without sending Swiss personal data across the border — tokenised on the way out, restored on the way back.

• Sovereign Shield
• AI security
• privacy

I re-ran the same secret-extraction attacks against the flagship models. Gemini 2.5 Pro folds to a forced schema 95% of the time — worse than the cheap tier — while Claude's flagship models drop the prefill surface entirely. The holes move between generations.

• K.E.V.I.N.
• AI security
• red-teaming

Gemini leaks under a forced JSON schema; Claude resists that but folds to prefill. Opposite weak spots, same secret — and one deterministic defense that catches both.

• K.E.V.I.N.
• AI security
• red-teaming

Six hand-written jailbreaks couldn't crack my hardened bot. Then I forced its reply into a JSON schema and it leaked the secret on turn one. Why structured output is the hole.

• K.E.V.I.N.
• AI security
• red-teaming

I built K.E.V.I.N.: one AI tries to extract a secret from another while three judges score each attempt. Three things 50 rounds of automated jailbreaking taught me.

• K.E.V.I.N.
• AI security
• red-teaming