VendorsAdversa AI
Adversa AI
Cybersecurity reports and statistics published by Adversa AI
5 categories1 reports
Research Reports
Reports and publications from Adversa AI
Recent Statistics & Reports
Agentic AI caused the most dangerous failures—crypto thefts, API abuses, and legal disasters, and Supply chain attacks.
7/31/2025•
AIAI security incidentsAgentic AI
35% of all real-world AI security incidents were caused by simple prompts.
7/31/2025•
AIAI security incidents
Some prompt injection incidents led to over $100,000 in real losses without requiring any code to be written.
7/31/2025•
AIAI security incidentsPrompt injection
Generative AI (GenAI) was involved in 70% of real-world AI security incidents.
7/31/2025•
AIAI security incidentsGen AI
AI security incidents have doubled since 2024
7/31/2025•
AIAI security incidents