BackSecurity
Security
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.
every piece of software, including learning systems, may be hacked by malicious users
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 Saghiri et al. (2022) (15)
Energy Consumption
6.6 Environmental harmAI systemUnintentionalPre-deployment
Data Issues
1.1 Unfair discrimination and misrepresentationAI systemUnintentionalOther
Robustness and Reliability
7.3 Lack of capability or robustnessAI systemUnintentionalPost-deployment
Cheating and Deception
7.2 AI possessing dangerous capabilitiesAI systemUnintentionalPost-deployment
Privacy
2.1 Compromise of privacy by leaking or correctly inferring sensitive informationAI systemOtherPre-deployment
Fairness
1.3 Unequal performance across groupsAI systemUnintentionalPre-deployment