• EPISODE 27: Ignore all previous instructions: Threat modelling AI Systems

  • Apr 24 2024
  • Length: 37 mins
  • Podcast
  • 5.0 out of 5 stars (1 rating)
EPISODE 27: Ignore all previous instructions: Threat modelling AI Systems cover art

EPISODE 27: Ignore all previous instructions: Threat modelling AI Systems

  • Summary

  • Welcome to Compromising Positions! The tech podcast that asks non-cybersecurity professionals what we in the industry can do to make their lives easier and help make our organisations more prepared to face ever-changing human-centric cyber threats! Welcome to the grand finale of season two of ‘Compromising Positions’, where we delve into the fascinating world of AI security. In this special episode, your hosts will guide you through the labyrinth of securing AI models, one step at a time.For those who prefer a quick overview, we offer an abridged version on Apple Podcasts and Spotify. This version deep dives into two key topics: Jeff’s unique mnemonic C-PTSD for threat modeling AI systems, and an intriguing discussion on the correlation between boredom, worm-killing, and AI efficiency gains.For those who crave a deeper dive, scroll down or visit our Youtube channel for the extended cut. This version includes everything from the regular version, plus:Jeff’s academic journey in AI at the University of HullLianne’s preparation for a 100 days of Code in Python for her MSc in Data Science and AI at Leeds Trinity UniversityA critical discussion on OpenAI’s transparency and the latest AI wearable technology, along with the complexities of consent and privacy in an ‘always recorded’ lifestyleWhether you choose the regular or extended version, we appreciate your support throughout season two. Stay tuned for more enlightening discussions in season three! Thank you for being a fantastic audience.We hope you enjoyed this episode - See you next time, keep secure, and don’t forget to ask yourself, ‘Am I the compromising position here?’ Keywords: Cybersecurity, AI, Threat Modelling, MSC, Data Science, IOT, Wearables, Data SecuritySHOW NOTESJeff’s article on C-PTSDLianne’s Article The (AI) Revolution will be BORING...And that's Okay!Wearables, Shareables, Unbearable? The IOT and AI Tech Nobody Asked for But Cybersecurity Criminals Love. Future of CybersecurityMSc in Artificial Intelligence - University of HullMSc in Data Science and Artificial Intelligence - Leeds Trinity UniversityPython Crash Course by Eric MatthesCodewarsIn Praise of Boring AI by Ethan MollickSeason Two Playlist - YoutubeVote for us! European Cybersecurity Blogger Awards and The Real Cyber AwardsABOUT LIANNE POTTERAs the Head of SecOps for the largest greenfield technology transformation project in Europe, Lianne is building a leading edge security team from scratch to meet the needs of a modern retail organisation while empowering her team to think innovatively to create new standards in best practices. Lianne has delivered talks across the globe to share her vision for a new type of security function. Drawing upon her expertise as a cyber-anthropologist (through her consultancy, The Anthrosecurist), her practical experience as a security-focused software developer and as a security practitioner; Lianne combines the human and the technical aspects of security to evangelise a cultural security transformation. She is on the advisory board for a community enterprise aimed at encouraging diversity in tech, is a published author, podcast regular and Host of Cybersecurity Podcast Compromising Positions, and won Computing.com’s Security Specialist of the Year for her work on human-centric approaches to security. In 2021 she won two awards for Security Leader of the Year 2021 and Woman of the Year in the Enterprise category and in 2023 she won Cyber Personality of the Year in The Real Cyber Awards. She is doing a Masters in AI and Data Science in 2024.LINKS FOR LIANNELinkedInCompromising Positions PodcastABOUT JEFF WATKINSJeff is Chief Product and Technology Officer for xDesign. He is a lifelong technologist with nearly 25 years’ experience in the industry, first having started coding at age 6. Having worked in the Financial Services, Healthcare and Retail industries, on enterprise and national scale programmes. Over the years he has become increasingly interested in Cybersecurity and AI and how both will shape our future, both technologically and the human impact. Jeff has founded multiple CyberSecurity teams and is currently working on several new pieces around the secure development and deployment of Generative AI based solutions. He is a tech blogger, writer, podcaster and host of Compromising Positions and public speaker, having recently keynote at the Webinale international web conference in Berlin.Jeff has a Masters in Cybersecurity and will be starting his Masters in AI and Data Science in 2024.LINKS FOR JEFFLinkedinCompromising Positions Podcast
    Show More Show Less

What listeners say about EPISODE 27: Ignore all previous instructions: Threat modelling AI Systems

Average customer ratings
Overall
  • 5 out of 5 stars
  • 5 Stars
    1
  • 4 Stars
    0
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0
Performance
  • 5 out of 5 stars
  • 5 Stars
    1
  • 4 Stars
    0
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0
Story
  • 5 out of 5 stars
  • 5 Stars
    1
  • 4 Stars
    0
  • 3 Stars
    0
  • 2 Stars
    0
  • 1 Stars
    0

Reviews - Please select the tabs below to change the source of reviews.