Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn strategies for building trustworthy AI systems through a comprehensive exploration of AI security and safety principles in this 24-minute conference talk. Discover how trust emerges as a multifaceted outcome when product and engineering teams collaborate to create AI that is aligned, explainable, and secure. Explore the fundamental equation that Trustworthy AI equals AI Security plus AI Safety, and understand the critical differences between these two components. Dive into three essential focus areas: MLSecOps, AI Red Teaming, and AI Runtime Security, and learn how these disciplines work together to achieve both security and safety objectives. Examine real-world trustworthy AI issues currently making headlines and gain access to practical resources including Modelscan for model security, PyRIT for red teaming, and various runtime security solutions. Understand how to effectively showcase trustworthy AI capabilities to customers and prospects through trust centers and transparency initiatives, making this essential knowledge for anyone involved in AI product development and deployment.
