How Anthropic’s Jailbreak Challenge Put AI Safety Defenses to the Test
hackerone.com | blog | #ai-security | #ai-safety | #red-teaming | #jailbreak | #llm | #claude | #hackerone | #ai-red-teaming | #anthropic | #constitutional-classifiers | #cbrn
Summary
Anthropic and HackerOne ran an AI red teaming challenge on a demo Claude 3.5 Sonnet to validate Constitutional Classifiers that block CBRN-related jailbreaks, awarding $55,000 to four teams.
- Published
- Collected
--- id: 1260 title: "How Anthropic’s Jailbreak Challenge Put AI Safety Defenses to the Test" source_domain: hackerone.com source_url: "https://www.hackerone.com/blog/how-anthropics-jailbreak-challenge-put-ai-safety-defenses-test" published_at: "2025-03-03 18:48" tags: ["ai-security", "ai-safety", "red-teaming", "jailbreak", "llm", "claude", "hackerone", "ai-red-teaming", "anthropic", "constitutional-classifiers", "cbrn"] phying_url: "https://phying.com/item/1260" lang: en --- # How Anthropic’s Jailbreak Challenge Put AI Safety Defenses to the Test ## Summary Anthropic and HackerOne ran an AI red teaming challenge on a demo Claude 3.5 Sonnet to validate Constitutional Classifiers that block CBRN-related jailbreaks, awarding $55,000 to four teams. ## Intelligence Metadata - **Sources:** hackerone.com - **Published:** 2025-03-03 18:48 - **Original:** https://www.hackerone.com/blog/how-anthropics-jailbreak-challenge-put-ai-safety-defenses-test - **Phying News:** https://phying.com/item/1260