How AI Can Deceive and be Deceived

8th Layer Insights

On this episode Perry sits down with Dr. Matthew Canham to explore ways in which AI can be weaponized against us, and how age old social engineering tactics can be used to trick large language models.

Guest:

• Dr. Matthew Canham (LinkedIn) (Website)

Books and References (Books are Amazon Associate Links and help support the show):

• Cognitive Security Institute YouTube Channel
• Cognitive Security Institute website
• YouTube video: BlackHat Presentation -- Me and My Evil Digital Twin: The Psychology of Human Exploitation by AI Assistants
• YouTube video: NEW AI Jailbreak Method SHATTERS GPT4, Claude, Gemini, LLaMA
• Not with a Bug, But with a Sticker: Attacks on Machine Learning Systems and What To Do About Them, by Ram Shankar Siva Kumar & Hyrum Anderson
• Six Thinking Hats, the de Bono Group
• Six Thinking Hats: Looking at Decision in Different Ways, MindTools
• AI + Six Thinking Hats, LifeArchitect.ai
• 8Li Season 4, episode 10: Artificial Intelligence Insights & Oddities

Perry's Books (Amazon Associate Links)

• Transformational Security Awareness: What Neuroscientists, Storytellers, and Marketers Can Teach Us About Driving Secure Behaviors, by Perry Carpenter
• The Security Culture Playbook: An Executive Guide To Reducing Risk and Developing Your Human Defense Layer by Perry Carpenter & Kai Roer

Production Credits:

Music and Sound Effects by Blue Dot Sessions, Envato Elements, & Storyblocks.

Artwork by Chris Machowski @ https://www.RansomWear.net/ and Mia Rune @ https://www.MiaRune.com.

8th Layer Insights theme music composed and performed by Marcos Moscat @ https://www.GameMusicTown.com/

Want to get in touch with Perry? Here's how:

• LinkedIn
• Twitter
• Instagram
• Email: perry [at] 8thLayerMedia [dot] com