BackSecurity threats
Security threats
Risk Domain
Using AI systems to develop cyber weapons (e.g., by coding cheaper, more effective malware), develop new or enhance existing weapons (e.g., Lethal Autonomous Weapons or chemical, biological, radiological, nuclear, and high-yield explosives), or use weapons to cause mass harm.
"Facilitating the conduct of cyber attacks, weapon development, and security breaches"(p. 31)
Entity— Who or what caused the harm
Intent— Whether the harm was intentional or accidental
Timing— Whether the risk is pre- or post-deployment
Part of Malicious Use
Other risks from Weidinger et al. (2023) (26)
Representation & Toxicity Harms
1.0 Discrimination & ToxicityAI systemUnintentionalPost-deployment
Representation & Toxicity Harms > Unfair representation
1.1 Unfair discrimination and misrepresentationAI systemUnintentionalPost-deployment
Representation & Toxicity Harms > Unfair capability distribution
1.3 Unequal performance across groupsAI systemUnintentionalPost-deployment
Representation & Toxicity Harms > Toxic content
1.2 Exposure to toxic contentAI systemUnintentionalPost-deployment
Misinformation Harms
3.0 MisinformationAI systemOtherPost-deployment
Misinformation Harms > Propagating misconceptions/ false beliefs
3.1 False or misleading informationAI systemOtherPost-deployment