Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore the dual nature of AI as both an accelerant for innovation and a potential security threat in this technical conference talk. Dive deep into real-world AI vulnerabilities through hands-on demonstrations from the terminal, witnessing live exploits and adversarial attacks that reveal how easily AI systems can be compromised. Learn about current attack vectors including LLM jailbreaking techniques and AI-driven zero-day exploits through concrete code examples and case studies. Discover defensive strategies to secure AI implementations, including prompt strengthening, implementing effective guardrails, detecting rogue AI agents, and conducting AI-specific red team exercises. Gain practical insights from Bar-El Tayouri, who leads Mend AI and brings extensive experience in cybersecurity and data science, as he demonstrates both offensive and defensive AI security techniques to help you harness AI's power while mitigating its risks.
