The Security and Privacy Implications of AI and Machine Learning

Presented at Still Hacking Anyway (SHA2017), Aug. 5, 2017, 12:20 p.m. (60 minutes)

What will the recent rapid progress in machine learning and AI mean for the fields of computer security and privacy? This talk gives a tour of some answers, and some unanswered questions. It will discuss new types of attacks and surveillance that are becoming possible due with modern neural networks, and some new research problems that the computer security community should be working on. #MachineLearning #Privacy Mostly this talk will focus on practical issues created by current machine learning progress. Though it's also interesting to consider what problems would be raised if progress is made towards "general" artificial intelligence that exhibits human-like autonomy and creativity, and we'll touch on a couple of questions about security, privacy and such hypothetical forms AI.

Presenters:

• Peter Eckersley
  Peter Eckersley is the Chief Computer Scientist at the Electronic Frontier Foundation (EFF). Peter Eckersley is the Chief Computer Scientist at the Electronic Frontier Foundation. Some of the projects he's started or co-founded have included HTTPS Everywhere, Panopticlick, Privacy Badger, the SSL Observatory, Certbot and Let's Encrypt. He's currently focused on studying the security, safety and privacy implications of machine learning and AI systems.

Links:

• https://program.sha2017.org/events/323.html

Similar Presentations:

• Black Hat USA 2020 Virtual / Superman Powered by Kryptonite: Turn the Adversarial Attack into Your Defense Weapon
• BSidesLV 2017 / The New Cat and Mouse Game: Attacking and Defending Machine Learning Based Software
• ShmooCon XI (2015) / Practical Machine Learning for Network Security