Attacks on GenAI see sensitive data leaked

New research reveals that 90 percent of successful attacks against GenAI have resulted in the leakage of sensitive data. The report from Pillar Security, based on real-world analysis of more than 2,000 AI applications, shows 20 percent of jailbreak attack attempts successfully bypassed GenAI application guardrails and adversaries needed an average of just 42 seconds to execute an attack. Attackers needed only five interactions on average with GenAI applications to complete a successful attack. The attacks exploited vulnerabilities at every stage of interaction with GenAI systems, underscoring the critical need for comprehensive security measures. The analyzed attacks also reveal a… [Continue Reading]