CybersecurityAgents5 min reading time

New Archestra's OpenAPPA Saturates Two Major Security Benchmarks with a 0% Attack Success Rate

InfoQ (AI, ML & Data)
Read the full article
Archestra launched OpenAPPA, an open-source security engine that prevents data leaks from prompt injection or hallucination in AI agents. It achieved a 0% attack success rate on major benchmarks, outperforming Claude Code and Microsoft FIDES. OpenAPPA enforces deterministic policies externally to the agent's execution, balancing strict security with operational utility.

More in Cybersecurity

Man Charged With Illegally Shipping Nvidia Chips to China

Covered by 5 sources

Rogue AI agents expose internet's frail foundation

Covered by 3 sources
Cybersecurity3 min read

OpenAI says its review into hacks, including on Australian government sites, is costing $500,000 a day

The Guardian