BackLimitations in adversarial robustness
Limitations in adversarial robustness
Risk Domain
Vulnerabilities that can be exploited in AI systems, software development toolchains, and hardware, resulting in unauthorized access, data and privacy breaches, or system manipulation causing unsafe outputs or behavior.
"AI models and systems are vulnerable to manipulation through adversarial inputs."(p. 13)
Entity: Who or what caused the harm
Intent: Whether the harm was intentional or accidental
Timing: Whether the risk is pre- or post-deployment
Other risks from Uuk et al. (2025) (60)
Control
7.1 AI pursuing its own goals in conflict with human goals or valuesAI systemIntentionalPost-deployment
Democracy
6.0 Socioeconomic & EnvironmentalOtherOtherOther
Discrimination
1.1 Unfair discrimination and misrepresentationOtherOtherPost-deployment
Economy
6.2 Increased inequality and decline in employment qualityOtherOtherPost-deployment
Environment
6.6 Environmental harmAI systemUnintentionalPost-deployment
Governance
6.5 Governance failureAI systemUnintentionalPost-deployment