A detailed breakdown of the updated OWASP Top 10 vulnerabilities for Large Language Models (LLMs), explaining threats like prompt injection, data poisoning, and supply chain risks, along with practical defense strategies.
Siyethaba Nxumalo, the 22-year-old founder of CipherGenix, outlines the critical need for AI-specific cybersecurity in healthcare, where compromised models directly impact patient lives. He details his journey of building a global startup from South Africa, emphasizing a customer-first approach, a multi-layered security architecture to combat threats like data poisoning and model theft, and the non-negotiable role of ethical, explainable AI in building trust and ensuring patient safety.
To build secure AI systems, we must first learn to break them. Katharine Jarmul explores the landscape of adversarial AI, detailing how attackers exploit fundamental weaknesses in deep learning models—from poisoned training data and overparameterization to the attention mechanism itself. This talk provides a practical taxonomy of attacks and a primer on building robust defenses.
Tech leader and investor Michelle Yi discusses the critical technical aspects of building trustworthy AI systems. She delves into adversarial attack and defense mechanisms, including red teaming, data poisoning, prompt stealing, and "slop squatting," and explores how advanced concepts like Constitutional AI and World Models can create safer, more reliable AI.