Aevrin AI Red Teaming
aevrin.net
5.5 Club score Visit aevrin.net
What the maker publishes
- Attack techniques
- The product lists more than 1,000 adversarial attack techniques. source
- Attack techniques
- The product lists 1000+ adversarial attack techniques. source
- Availability
- The product page describes AI Red Teaming as a separate platform and invites visitors to explore it; it does not state a launch date or availability status. source
- Availability
- The page calls AI Red Teaming a separate platform and links to an Explore AI Red Teaming action. source
- Framework mapping
- The product maps tests to the OWASP LLM Top 10. source
- Framework mapping
- The product lists OWASP LLM Top 10 mapping. source
- Pricing
- The product page does not state an AI Red Teaming price or plan. source
- Purpose
- AI Red Teaming is presented as a product for testing, auditing, and protecting chatbots put in front of people. source
- Purpose
- AI Red Teaming is described as a platform to test, audit, and protect chatbots put in front of people. source
- Runtime protection
- The product lists a runtime policy firewall. source
- Runtime protection
- The product lists a runtime policy firewall. source
- Testing focus
- The product targets prompt injection, jailbreaks, sensitive data leakage, policy failures, and harmful outputs. source
- Testing focus
- The product targets prompt injection, jailbreaks, sensitive data leakage, policy failures, and harmful outputs. source
- Timing
- Aevrin says the product finds issues before launch and blocks them in production. source
- Timing
- Aevrin says issues are found before launch and blocked in production. source
Checked against the maker's pages on 9 Oct 2026.