Webinar: Exposing the Shadows: Real-World Attacks on AI Systems

In this session, we discuss real-world examples of compromised AI systems, including the Samsung data leak via ChatGPT and the use of AI chatbots in phishing scams. We analyze the attack methods and their impact on security and privacy and suggest strategies for strengthening AI systems against these threats.

This session will dive deeper into:

• Real-world case studies of AI system breaches, including known corporate incidents
• Analysis of attack vectors unique to AI and machine learning pipelines
• Exploration of how prompt injection, model poisoning, and output manipulation are used by threat actors
• Discussion of regulatory and ethical implications for securing AI systems

Speakers:

• Amit Chita, Field CTO – Mend.io
• Bar-el Tayouri, Head of Mend AI – Mend.io