ISO/IEC TR 24028:2020
Vulnerabilities, threats and challenges – ISO/IEC TR 24028:2020

ISO/IEC TR 24028:2020 8.2.3: Adversarial attacks

Inputs crafted to cause a model to produce wrong outputs while appearing normal, exploiting the model's sensitivity to small perturbations.

Maintained by Gerard Blokdyk

Other controls in Vulnerabilities, threats and challenges – ISO/IEC TR 24028:2020

Query this from an agent

The graph holds this control, the 0 it maps to, and the evidence behind each claim, over MCP and REST.