Quick Look: No Exemptions for AI: New Technology = New Attack Surface
summary
Describes security risks specific to AI systems such as Dolphin attacks and adversarial inputs that confuse self-driving cars, framing them as new attack surfaces. Gives practical guidance and tips for safely integrating machine learning into adversarial environments, based on the speaker’s experience.
AI-written summary · about
chapters (9)
- 0:00Intro
- 0:30Session Outline
- 1:24What's Al Deception?
- 2:47Why is it possible?
- 4:31Security Lifecycle
- 6:56Where's Al Deception Applicable?
- 8:17Security Modeling
- 9:31Mitigation
- 10:41Safe Alin Cyber Applications
related talks
21mAI Deception: Fooling (Artificial) Intelligence Is Easier than You Think
13mQuick Look: AI in Cybersecurity: A Balancing Force or a Disruptor?
01mQuick Look: Really a New Mouse Trap? Exploring Risks with Artificial Intelligence
37mFundamentals of AI safety and security
01h 05mNavigating the Security and Privacy Landscape of Modern AI
47mWhat AI Security means for you as a developer: Time-focused approach
22mAdversarial AI: Why it Matters Now
49mThe Intersection of AI and Cybersecurity