AI systems – especially those powered by LLMs – introduce new and often misunderstood attack surfaces. From prompt injection to data poisoning, and model behavior manipulation, this panel brings together security experts who are studying and fighting these threats in the wild. Attendees will walk away with real attack examples, mitigation strategies, and key considerations to build AI threat models that matter.
Intervenants :
- Moderator: Heather Kuhn, Sr. Privacy Counsel, BigID
- Heather Holliday, Vice President, Technology Risks & Controls Lead, JPMorganChase
- Parul Khanna, Director Technology Governance and Control, Manulife
- Alyssa Columbus, PhD Candidate & NASA Datanaut