SecAppDev 2026 - Offensive security
SecAppDev 2026 offers three days of in-depth lectures and two days of hands-on workshops. Use the buttons below to navigate between the topics.
AI / ML security
OWASP top 10
Authorization
Architecture
Secure Coding
Web security
Governance
Application Security
Privacy
Offensive security
How to (still) trick AI: Adversarial ML for Today
Introductory lecture by Katharine Jarmul
There's many known (and still being discovered) attack vectors against deep learning models. In this session, we'll walk through some of the history of adversarial ML and deep learning and find what's changed and what's stayed the same.
Key takeaway: AI/DL models are inherently nondeterministic and have other properties that allow for old, new and interesting attacks.