Exposure Pathways
How does AI-enabled harm reach the people and systems it affects? Exposure pathways describe the transmission mechanism — the causal link between an AI system's behavior and the harm experienced.
Adversarial Targeting
AI is weaponized by a threat actor to directly target specific victims. The AI system is the instrument of intentional harm, not a passive intermediary.
28 incidentsAlgorithmic Decision Impact
Harm occurs through AI-driven decision-making processes that affect the victim without requiring their direct interaction with the system. Includes scoring, ranking, filtering, and automated adjudication.
27 incidentsDirect Interaction
Harm occurs through the victim's direct use of or interaction with an AI system. The victim engages with the system and is harmed through that engagement.
35 incidentsEconomic Displacement
Harm occurs through AI-driven restructuring of labor markets, economic relationships, or market dynamics. Victims are harmed by structural economic change, not by a specific system interaction.
2 incidentsInfrastructure Dependency
Harm occurs because victims depend on AI-managed critical systems that fail, are compromised, or behave unpredictably. The harm vector is systemic dependency, not direct use.
10 incidentsAbout Exposure Pathways
Exposure pathways are a taxonomy dimension that captures how harm reached the affected parties. This is distinct from:
- Threat patterns — describe what the attacker did (the attack type)
- Harm types — describe what damage occurred (the consequence)
- Exposure pathways — describe the transmission mechanism (how harm traveled from AI system to victim)
Most incidents have exactly one exposure pathway. Two may apply when distinct transmission mechanisms affect different groups within the same incident.
For the full classification methodology, see the Taxonomy page or the Methodology.
5 exposure pathways · View threat domains · View affected groups