Open-source EuroSafeGuard outdetects 16 guard models on jailbreaks, halving PAIR attack success
ZhijingJin · x · 2026-11-07
EuroSafeAI released EuroSafeGuard, the first fully open implementation of Anthropic's Constitutional Classifiers++ design. Calibrated to the same false-positive rate, it hits 93% mean recall on held-out jailbreak templates, beating 16 open guards including HaloGuard (90%). Against PAIR search attacks, only 20% of behaviors get through versus 49% for the strongest open alternative.
Related event: EuroSafeGuard Tops 16 Open Guardrails With 93% Jailbreak Detection(3 posts)→
More from Safety
- Nigerian-American scientist Chinasa T. Okolo named to TIME100 AI list — ChinasaTOkolo · 2026-11-07
- Ex-OpenAI policy head: safety reports yield diminishing returns without human-level framing — deanwball · 2026-11-07
- OpenAI employee pleads not guilty to secretly bugging company office — Polymarket · 2026-11-07
- California bill would force frontier AI labs to disclose compute allocation for safety — ohlennart · 2026-11-07
- Critic: Anthropic backs recursive self-improvement at full speed while only talking about safety — peterwildeford · 2026-11-07
- EuroSafeGuard adds only 1% compute overhead for full-traffic jailbreak defense — ZhijingJin · 2026-11-07