DSML 2018
Dependable and Secure Machine Learning


Workshop Program - Monday, 25 June 2018

08:30-09:00 Registration
09:00-09:15 Welcome to DSN-DSML 2018
Session 1: Keynote Talk
09:15-10:15

10:15-10:30
The Road to Resilient Computing in Autonomous Driving is Paved with Redundancy
Nirmal R. Saxena, NVIDIA
Q&A
10:30-11:00 Coffee Break
Session 2: Dependability and Trust
11:00-11:30


11:30-12:00


12:00-12:30
Fairness and Transparency of Machine Learning for Trustworthy Cloud Services
Nuno Antunes, Leandro Balby, Flavio Figueiredo, Nuno Lourenco, Wagner Meira Jr., Walter Santos

Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning
Mahdieh Abbasi, Arezoo Rajabi, Christian Gagn'e, Rakesh B. Bobba

Model, Data and Reward Repair: Trusted Machine Learning for Markov Decision Processes
Shalini Ghosh, Ashish Tiwari, Susmit Jha, Patrick Lincoln
12:30-14:00 Lunch Break
Session 3: Keynote Talk
14:00-15:00

15:00-15:15
Systematic Testing and Verification of Deep Learning Systems
Suman Jana, Columbia University
Q&A
15:30-16:00 Coffee Break
Session 4: Attacks and Defenses
16:00-16:30


16:30-17:00
On the Limitation of MagNet Defense against L1-based Adversarial Examples
Pei-Hsuan Lu, Pin-Yu Chen, Kang-Cheng Chen, Chia-Mu Yu

DCN: Detector-Corrector Network Against Evasion Attacks on Deep Neural Network
Jing Wen, Lucas C.K. Hui, Siu-Ming Yiu, Ruoqing Zhang
Joint Panel Discussion with the DSN SSIV Workshop
17:00-18:00 How will we be able to trust self-driving cars?
Panelists: Philippe Quéré (Renault), Nirmal R. Saxena (Nvidia), Johan Karlsson (Chalmers University)
Moderator: Doug Blough (Georgia Institute of Technology)

Keynotes


Systematic Testing and Verification of Deep Learning Systems
Suman Jana, Columbia University

Speaker Bio:
Suman Jana is an assistant professor in the department of computer science at Columbia University since January 2016. His primary research interest is in the field of computer security and privacy. His research has won six best paper awards including one at the Symposium on Operating Systems Principles (SOSP) 2017 and two at the IEEE Symposiums on Security and Privacy (S&P) 2014 and 2016. His work has led to reporting and fixing of around 250 high-impact security vulnerabilities across a wide range of software. His research software has also been incorporated as part of Google's malware detection infrastructure, Mozilla Firefox, and Apache Cordova.


The Road to Resilient Computing in Autonomous Driving is Paved with Redundancy
Nirmal R. Saxena, NVIDIA

Speaker Bio:
Nirmal R. Saxena is currently a distinguished engineer at NVIDIA and is responsible for HPC and Automotive Resilient Computing. From 2006 through 2015, Nirmal was associated with Inphi Corp as CTO for Storage & Computing and with Samsung Electronics as Sr. Director working on fault-tolerant DRAM memory and storage array architectures. During 2006 through 2011, Nirmal held roles as a Principal Architect, Chief Server Hardware Architect & VP at NVIDIA. From 1991 through 2009, he was also associated with Stanford University's Center for Reliable Computing and EE Department as Associate Director and Consulting Professor respectively. During his association with Stanford University, he taught courses in Logic Design, Computer Architecture, Fault-Tolerant Computing, supervised six PhD students and was co-investigator with Professor Edward J. McCluskey on DARPA's ROAR (Reliability Obtained through Adaptive Reconfiguration) project. Nirmal held senior technical and executive positions at Alliance Semiconductors, Chip Engines, Tiara Networks, Silicon Graphics, HaL Computers, and Hewlett Packard. Nirmal received his Ph.D. EE degree (1991) from Stanford University. He is a Fellow of the IEEE (2002) and was cited for his contributions to reliable computing.