Evasion Attack on AI Classifier
How adversarial examples can be crafted to evade AI classification systems, with theory and an experimental environment using ART.
Read →02 posts on record
Post
September 18, 2025 · 8 min read
Excessive Agency in AI Systems
Investigating how AI systems can exceed their intended boundaries and how insecure agent design leads to vulnerabilities through a real-world example.
AI SecurityGenAIPrompt Injection
Read note →
Earlier notes