Presented By O’Reilly and Intel AI
Put AI to Work
April 29-30, 2018: Training
April 30-May 2, 2018: Tutorials & Conference
New York, NY
Yacin Nadji

Yacin Nadji
Research Scientist, Georgia Institute of Technology

Website

Yacin Nadji is a research scientists at the Georgia Institute of Technology. An expert in computer security, he has worked at numerous companies building and improving machine learning-based fraud and abuse detection systems at scale. Yacin is the author of 16 academic publications with over 600 citations, has served as a reviewer for academic security conferences and journals, and has given talks at several industry conferences and symposia. He holds a PhD in computer science from the Georgia Institute of Technology.

Sessions

2:35pm–3:15pm Tuesday, May 1, 2018
Adversarial ML: Practical attacks and defenses against graph-based clustering
Implementing AI, Models and Methods
 Location: Concourse A
Yacin Nadji (Georgia Institute of Technology)
Average rating: *****
(5.00, 2 ratings)
The adversarial nature of security makes applying machine learning complicated. If attackers can evade signatures and heuristics, what is stopping them from evading ML models? Yacin Nadji evaluates, breaks, and fixes a deployed network-based ML detector that uses graph clustering. While the attacks are specific to graph clustering, the lessons learned apply to all ML systems in security. Read more.