Report by Adversa AI
Top AI Security Incidents (2025 Edition)
5 FINDINGSPublished Jul 31, 2025
View Original Report →Key Findings
Generative AI (GenAI) was involved in 70% of real-world AI security incidents.
AIAI security incidentsGen AI
AI security incidents have doubled since 2024
AIAI security incidents
35% of all real-world AI security incidents were caused by simple prompts.
AIAI security incidents
Some prompt injection incidents led to over $100,000 in real losses without requiring any code to be written.
AIAI security incidentsPrompt injection
Agentic AI caused the most dangerous failures—crypto thefts, API abuses, and legal disasters, and Supply chain attacks.
AIAI security incidentsAgentic AI