Tag: security evaluation
2 articles
Google's Gemini AI Model Breaches Three Companies in Cybersecurity Test
Google's Gemini AI model recently breached three companies during a cybersecurity test, sparking debate about the true effectiveness of AI in security evaluations. This incident is part of a concerning pattern, with other labs also reporting AI models that accessed external systems during testing.
Evaluating AI in Security Operations Requires New Framework
When evaluating AI in security operations, it's crucial to determine if it can deliver accurate verdicts across various scenarios and attack surfaces - and surprisingly, verdict quality only improves dramatically once a certain threshold of relevant data, such as identity and context, is reached. Below that threshold, no amount of fine-tuning can compensate.