AI Reliability Against Adversarial Inputs

Summit Track: 
Technical Insights I

As artificial intelligence solutions are becoming ubiquitous, the security and reliability of AI algorithms is becoming an important consideration and a key differentiator for both solution providers and end users. AI solutions, especially those based on deep learning, are vulnerable to adversarial inputs, which can cause inconsistent and faulty system responses. Since adversarial inputs are intentionally designed to cause an AI solution to make mistakes, they are a form of security threat. Although security-critical functions like login based on face, voice or fingerprint are the most obvious solutions requiring robustness against adversarial threats, many other AI solutions will also benefit from robustness against adversarial inputs, as this enables improved reliability and therefore enhanced user experience and trust. In this presentation, we will explore selected adversarial machine learning techniques and principles from the point of view of enhancing the reliability of AI-based solutions.


Gokcen Cilingir

AI Software Architect, Intel

Gokcen Cilingir is a Ph.D., practicing AI technologies since 2005. She worked in many domains including bioinformatics, speech and audio processing, computer vision and adversarial machine learning. She has been an AI software architect since 2013 at Intel. She lives in San Jose, California with her family and enjoys family time with her daughter and son.

Li Chen

Data Scientist and Research Scientist, Intel

Li Chen is a data scientist and research scientist in the Security and Privacy Lab at Intel Labs, where she focuses on developing state-of-the-art robust machine learning algorithms for security with applications in threat detection and computer vision in adversarial settings. She is the principal investigator and research lead at the Intel Science & Technology Center on Adversary-Resilient Security Analytics. Li Chen received her PhD from Johns Hopkins University. Her research interests include machine learning, representation learning and differential privacy. Her research has been featured in pioneering journals and conferences including IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Security and Privacy, ACM CCS, ACSAC, Annals of Applied Statistics, Parallel Computing, AAAI Conference on Artificial Intelligence and SPIE. She has given more than 50 technical presentations, including at the Joint Statistical Meeting, AAAI, International Joint Conference on Artificial Intelligence and Spring Research Conference on Statistics and Industry Technology.

See you at the Summit! May 20-23 in Santa Clara, California!
Register today and reserve your hotel room!