Uploaded September 2023 | Updated September 2026, 2 weeks ago
The Insecurity of Deep Neural Networks
Machine learning has made tremendous progress in the last decade, solving a broad range of tasks ranging from recognizing objects to chatting in natural language. However, today's amazing systems have a dark side: They are incredibly easy to fool by malicious actors. In this talk, I will describe some of these attacks, such as adversarial examples and trapdoored systems, and try to solve the mystery of what makes systems which are so powerful so vulnerable.
The 10th Heidelberg Laureate Forum took place from September 24–29, 2023. #HLF23
The Heidelberg Laureate Forum (HLF) is an annual networking conference where 200 carefully selected young researchers in mathematics and computer science spend a week interacting with the laureates of the most prestigious awards in their disciplines: the Abel Prize, ACM A.M. Turing Award, ACM Prize in Computing, Fields Medal, IMU Abacus Medal and Nevanlinna Prize.
The opinions expressed in the videos do not necessarily reflect the views of the Heidelberg Laureate Forum Foundation or any other person or associated institution involved in the making and distribution of these videos.
More information on the Heidelberg Laureate Forum:
heidelberg-laureate-forum.org
Follow us on social media!
Blog: scilogs.spektrum.de/hlf
LinkedIn: linkedin.com/company/heidelberg-laureate-forum-foundation
X/Twitter: twitter.com/HLForum
Instagram: instagram.com/hlforum
Facebook: facebook.com/HeidelbergLaureateForum
The Insecurity of Deep Neural Networks
Machine learning has made tremendous progress in the last decade, solving a broad range of tasks ranging from recognizing objects to chatting in natural language. However, today's amazing systems have a dark side: They are incredibly easy to fool by malicious actors. In this talk, I will describe some of these attacks, such as adversarial examples and trapdoored systems, and try to solve the mystery of what makes systems which are so powerful so vulnerable.
The 10th Heidelberg Laureate Forum took place from September 24–29, 2023. #HLF23
The Heidelberg Laureate Forum (HLF) is an annual networking conference where 200 carefully selected young researchers in mathematics and computer science spend a week interacting with the laureates of the most prestigious awards in their disciplines: the Abel Prize, ACM A.M. Turing Award, ACM Prize in Computing, Fields Medal, IMU Abacus Medal and Nevanlinna Prize.
The opinions expressed in the videos do not necessarily reflect the views of the Heidelberg Laureate Forum Foundation or any other person or associated institution involved in the making and distribution of these videos.
More information on the Heidelberg Laureate Forum:
heidelberg-laureate-forum.org
Follow us on social media!
Blog: scilogs.spektrum.de/hlf
LinkedIn: linkedin.com/company/heidelberg-laureate-forum-foundation
X/Twitter: twitter.com/HLForum
Instagram: instagram.com/hlforum
Facebook: facebook.com/HeidelbergLaureateForum
