NIST publishes adversarial machine-learning risk taxonomy

DoomBench assesses “NIST publishes adversarial machine-learning risk taxonomy” as evidence moving away from doom, with magnitude 29 and confidence 97 out of 100 in the safety and alignment category.

The DoomBench assessment of “NIST publishes adversarial machine-learning risk taxonomy” is based on reporting from NIST and records the editorial rationale, source quality, attribution, and revision history.

DoomBench summarizes “NIST publishes adversarial machine-learning risk taxonomy” as follows: NIST published AI 100-2e2025, a standardized taxonomy covering evasion, poisoning, privacy and generative-AI misuse attacks plus mitigations...