Threat Prompt: AI Security
AI is ushering in a new era of sophisticated cyber attack and defence. In this session, we will explore AI from a hacker’s perspective.
The first half is about the security of AI and starts with a fast-paced introduction to AI tech. Building on this foundation, we survey the major AI vulnerability classes, attacks and defences, supported by examples. This section concludes with AI policy recommendations help you influence debate on AI within your organisation.
The second half is about applying AI to cyber attack and defence. Demos will cover practical use cases and include prompts and patterns for penetration testers, developers, cloud security engineers, incident responders and policy writers.
Some say AI is the next existential threat since nuclear, yet so few risk and security professionals are applying their talent to make it safe. My talk proposal is to increase engagement by our community in the AI domain. The pace of AI development is far outstripping our understanding of the risks and countermeasures. This is not cloud computing where we can show up late – we need to be in the arena sooner rather than later.
My talk is split into two parts; the first part is a level set for attendees on what AI is and the security risks/countermeasures. This part concludes with talking points for influence on AI policy. The second half is live demos to illustrate the powerful lever AI gives us (and the bad guys). My goal is that attendees walk away with at least three solid ideas about using AI for their security work. I will also share specific tactics I use to avoid getting tripped up by AI hallucinations and other nonsense.
About the Speaker
Craig Balding is the former Group Security CTO for Barclays PLC, the proud founder and original Director of the GE Red Team and now an independent cybersecurity consultant based out of Budapest. I left the corporate world after 20 years in demanding cyber security roles to spend more time with my family.