AI has emerged as a transformative force, rapidly integrating into our lives. While it has the potential to revolutionize human life and businesses, some significant threats and challenges need to be addressed – A new era of innovation and opportunity where the stakes are high. Here, the Secure development of AI is of paramount importance in realizing AI’s transformative potential.

This talk will delve into key strategies and opportunities for enhancing trust in AI and harnessing AI for cybersecurity. A comprehensive view of secure AI practices. It will encourage the audience to think critically of threats with AI and explore the intersection of AI and cybersecurity, ultimately ensuring secure innovation and safeguarding digital landscapes.

Takeaways from your talk:

• Understanding the evolving threat landscape in AI (and using AI, eg: deepfakes). Will also cover challenges such as biases. Understanding the impact of AI attacks such as data poisoning and model tampering.
• Overview of Secure AI Practices and Strategy
• Security culture – shift left movement and what it is for AI
• Testing strategy (eg: threat modeling (whiteboard hacking))
• Regulatory measures that development at companies need to comply (eg OWASP for passing the audit, EU AI ACT, US AI Bill)