AI Meets Security Symposium '19     

AI Meets Security Symposium '19 - overview

The AI Meets Security Symposium '19 is being held in conjunction with the IBM Research AI Week at the MIT-IBM Watson AI Lab in September 2019.

 

Description

As cyber security threats to enterprises and the cloud continue to become more sophisticated, stealthy, and devastating—some of which even weaponize AI technologies—, security operations teams struggle to keep up with detecting, managing, and countering cyber attacks, as well as proactively deploying protective measures. The security industry and practitioners are experimenting with AI and machine learning technologies in different areas of security operations, including the identification of security relevant (mis)behaviors and malware, extraction and consolidation of threat intelligence, reasoning over security alerts, and recommendation of countermeasures and/or protective measures.

At the same time, adversarial attacks on machine learning systems have become an indisputable threat. Attackers can compromise the training of machine learning models by injecting malicious data into the training set (so-called poisoning attacks), or by crafting adversarial samples that exploit the blind spots of Machine Learning models at test time (so-called evasion attacks). Adversarial attacks have been demonstrated in a number of different application domains, including malware detection, spam filtering, visual recognition, speech-to-text conversion, and natural language understanding. Devising comprehensive defenses against poisoning and evasion attacks by adaptive adversaries is still an open challenge. Thus, gaining a better understanding of the threat by adversarial attacks and developing more effective defense systems and methods is paramount for the adoption of Machine Learning systems in security-critical real-world applications.

 

Agenda

8:45am– 9:00am	Welcome
9:00am– 9:55am	Alexandre Rebert (ForAllSecure) The World’s First All-Machine Hacking Competition
9:55am–10:00am	Break
10:10am–11:05am	Tudor Dumitraș (University of Maryland College Park) Research Challenges for the Security of Machine Learning
11:05am–12:00pm	Venkat Venkatakrishnan (University of Illinois at Chicago) Intrusion Detection & Attack Scenario Reconstruction using Information Flow Analysis on Provenance Graphs
12:00pm–1:00pm	Lunch
1:00pm–1:55pm	Aleksander Madry (MIT) A New Perspective on Adversarial Perturbations
1:55pm–2:50pm	Nicolas Papernot (University of Toronto) A Marauder's Map of Security and Privacy in Machine Learning
2:50pm–3:45pm	Zico Kolter (Cargegie Mellon University) Provably robust deep learning: methods and challenges
3:45pm–4:00pm	Break
4:00pm–5:00pm	Mathieu Sinn and Beat Buesser (IBM Research) Tutorial on the IBM Adversarial Robustness 360 Toolbox

 

Venue

Mezzanine Lounce (307)
Stratton Student Center, 84 Massachusetts Ave. Cambridge, MA 02139

 

Steering Committee

• Ian Molloy (IBM Research)
• JR Rao (IBM Research)
• Mathieu Sinn (IBM Research)
• Marc Ph. Stoecklin (IBM Research)