DSML 2022
Dependable and Secure Machine Learning

Workshop Program - Monday, 27 June 2022

8:30 ET Welcome to DSN-DSML 2022
Saurabh Jha, IBM Research
Session 1: Keynote Talk
08:45 ET

09:45 ET
Safety and Resilience of Autonomous Vehicles
Siva Kumar Sastry Hari, NVIDIA
10:00 ET Coffee Break
Session 2: Robustness of Control Systems
Session Chair: Saurabh Jha
10:30 ET

10:50 ET

11:10 ET

11:30 ET
Autonomous Attack Mitigation for Industrial Control Systems [Teaser video]
John Mern, Kyle Hatch, Ryan Silva, Cameron Hickert, Tamim Sookoor, Mykel J. Kochenderfer

Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems [Teaser video]
Xugui Zhou, Maxfield Kouzel, Homa Alemzadeh

Talk: Towards Building Resilient Ensembles against Training Data Faults
Abraham Chan, Arpan Gujarati, Karthik Pattabiraman, Sathish Gopalakrishnan

Talk: General Probability in Coq [Teaser video]
Avraham Shinnar, Barry Trager

12:00 ET Lunch Break
Session 3: Keynote Talk
13:30 ET

14:30 ET
On the Semantic AI Security in CPS: The Case of Autonomous Driving [slides]
Alfred Chen, UC Irvine
14:45 ET Discussion and Closing
Virtual Session: ML Systems


On the Impact of Non-IID data on the Performance and Fairness of DP Federated Learning [Teaser video]
Saba Amiri, Adam Belloum, Eric Nalisnick, Sander Klous, Leon Gommans

Federated Learning with Anomaly Client Detection and Decentralized Parameter Aggregation
Shu Liu, Yanlei Shang

A Novel Robust Framework for Adaptive Selection of Filter Ensembles to Detect Adversarial Inputs
Arunava Roy, Dipankar Dasgupta


Safety and Resilience of Autonomous Vehicles
Siva Kumar Sastry Hari, NVIDIA

Abstract: Autonomous Vehicles are being increasingly integrated into our lives thanks to rapid advancements in AI and computing technologies. These systems use complex algorithms to perceive the surroundings and plan an efficient trajectory in real-time. Safety remains an important consideration for the autonomous vehicles. Before a large-scale deployment, the system vendors are expected to perform a thorough safety evaluation of the autonomous system and demonstrate how the system mitigates unexpected events. In this talk, I will present a broad overview of the area, identify outstanding research challenges, and summarize a few motivating example solutions being developed to address the challenges.

Speaker Bio: Siva Hari is a Senior Research Scientist in the Architecture Research Group at NVIDIA. His research interests are in the fields of computer architecture, system design, and artificial intelligence, with focus on resilience, safety, and efficiency of Autonomous and High-Performance Computing Systems. Four of his papers were recognized as IEEE Micro's Top Picks in 2022 and 2013, Best Research Paper Award at ISSRE 2020, and Best Paper Award Runner-up at DSN 2018, respectively. He received the David J. Kuck Outstanding Ph.D. Thesis Award by the CS Department at the University of Illinois at Urbana-Champaign, where he obtained his Ph.D. He obtained his bachelor's degree in Computer Science and Engineering from the Indian Institute of Technology (IIT) Madras.

On the Semantic AI Security in CPS: The Case of Autonomous Driving
Alfred Chen, UC Irvine

Abstract: Recent years have witnessed a global phenomenon in the real-world development, testing, deployment, and commercialization of AI-enabled Cyber-Physical Systems (CPSs) such as autonomous driving cars, drones, industrial and home robots. These systems are rapidly revolutionizing a wide range of industries today, from transportation, retail, and logistics (e.g., robo-taxi, autonomous truck, delivery drones/robots), to domotics, manufacturing, construction, and healthcare. In such systems, the AI stacks are in charge of highly safety- and mission-critical decision-making processes such as obstacle avoidance and lane-keeping, which makes their security more critical than ever. Meanwhile, since these AI algorithms are only components of the entire CPS system enclosing them, their security issues are only meaningful when studied with direct integration of the semantic CPS problem context, which forms what we call the “semantic AI security” problem space and introduces various new AI security research challenges. In this talk, I will focus on our recent efforts on the semantic AI security in one of the most safety-critical and fastest-growing AI-enabled CPS today, Autonomous Driving (AD) systems. Specifically, we performed the first security analysis on a wide range of critical AI components in industry-grade AD systems such as 3D perception, sensor fusion, lane detection, localization, prediction, and planning, and in this talk I will describe our key findings and also how we address the corresponding semantic AI security research challenges. I will conclude with a recent systemization of knowledge (SoK) we performed for this growing research space, with a specific emphasis on the most critical scientific gap we observed and our solution proposal.

Speaker Bio: Alfred Chen is an Assistant Professor of Computer Science at University of California, Irvine. His research interest spans AI security, systems security, and network security. His most recent research focuses are AI security in autonomous driving and intelligent transportation. His works have high impacts in both academic and industry with 30+ research papers in top-tier venues across security, mobile systems, transportation, software engineering, and machine learning; a nationwide USDHS US-CERT alert, multiple CVEs; 50+ news coverage by major media such as Forbes, Fortune, and BBC; and vulnerability report acknowledgments from USDOT, Apple, Microsoft, etc. Recently, his research triggered 30+ autonomous driving companies and the V2X standardization workgroup to start security vulnerability investigations; some confirmed to work on fixes. He co-founded the AutoSec workshop (co-located with NDSS), and co-created DEF CON's first AutoDriving-themed hacking competition. He received various awards such as NSF CAREER Award, ProQuest Distinguished Dissertation Award, and UCI Chancellor's Award for mentoring. Chen received Ph.D. from University of Michigan in 2018.