Critical infrastructure component failures when integrated with AI systems
AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.
"When relying on GPAI in critical infrastructure, there may be common mode failures that begin with vulnerabilities or robustness issues in the underlying model architecture or training setup. These failures may happen accidentally (in edge-cases) or due to adversarial inputs to the AI systems [58]."(p. 46)
Supporting Evidence (1)
"For example, a failure in the scheduling software of a chemical plant caused by an adversarial keyword can cause damage to physical property through halting critical processes (e.g., cooling, mixing of reactants)."(p. 46)
Other risks from Gipiškis2024 (144)
Direct Harm Domains (content safety harms)
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Violence and extremism
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Hate and toxicity
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Sexual content
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Child harm
1.2 Exposure to toxic contentDirect Harm Domains (content safety harms) > Self-harm
1.2 Exposure to toxic content