AI Red Team: Safety vs. Security
blog.sentry.security | blog | #ai-security | #prompt-injection | #llm | #ai-red-teaming | #threat-modeling | #safety
Summary
AI red teaming should separate security from safety: security covers compromise of AI systems like prompt injection, while safety addresses harmful misuse such as LLM-enabled malware.
- Published
- Collected
--- id: 7460 title: "AI Red Team: Safety vs. Security" source_domain: blog.sentry.security source_url: "https://blog.sentry.security/ai-red-teaming-safety-vs-security/" published_at: "2025-01-16T15:25:44Z" tags: ["ai-security", "prompt-injection", "llm", "ai-red-teaming", "threat-modeling", "safety"] phying_url: "https://phying.com/item/7460" lang: en --- # AI Red Team: Safety vs. Security ## Summary AI red teaming should separate security from safety: security covers compromise of AI systems like prompt injection, while safety addresses harmful misuse such as LLM-enabled malware. ## Intelligence Metadata - **Sources:** blog.sentry.security - **Published:** 2025-01-16T15:25:44Z - **Original:** https://blog.sentry.security/ai-red-teaming-safety-vs-security/ - **Phying News:** https://phying.com/item/7460