IEEE Workshop on Assured Autonomous Systems (WAAS) 2020

WAAS 2020


Engineering & Computer Science (General)



Workshop on Assured Autonomous Systems (WAAS)
MAY 21, 2020 AT THE HYATT REGENCY, SAN FRANCISCO, CA
https://www.ieee-security.org/TC/SPW2020/WAAS/
Important Dates
- Paper submission deadline: 2/3/2020 (Anywhere on Earth)
- Acceptance notification: 2/17/2020
- Publication-ready Papers Due: 3/6/2020
- Workshop: 5/21/2020
Keynote Speaker
- Dr. Sandeep Neema
The Workshop on Assured Autonomous Systems (WAAS) plans to address the gap that exists between theory-heavy autonomous systems and algorithms and the privacy, security, and safety of their real-world implementations. Advances in machine learning and artificial intelligence have shown great promise in automating complex decision-making processes across transportation, critical infrastructure, and cyber infrastructure domains. Practical implementations of these algorithms require significant systems engineering and integration support, especially as they integrate with the physical world. This integration is wrought with artificial intelligence (AI) safety, security, and privacy issues.
The primary focus of this workshop is the: (1) detection of, (2) response to, and (3) recovery from AI safety, security, and privacy violations in autonomous systems. Key technical challenges include discriminating between application-layer data breaches and benign process noises, responding to breaches and failures in real-time systems, and recovering from decision making failures autonomously.
WAAS seeks contributions on all aspects of AI safety, security, and privacy in autonomous systems. Papers that encourage the discussion and exchange of experimental and theoretical results, novel designs, and works in progress are preferred. Topics of interest include (but are not limited to):
AI Safety
- Detecting dataset anomalies that lead to unsafe AI decisions
- Engineering trusted AI software architectures
- Status of existing approaches in ensuring AI/ML safety and gaps to be addressed
- AI safety considerations and experience from industry
- Evaluating safety of AI systems according to their potential risks and vulnerabilities
- Resilient, explainable deep learning, and interpretable machine learning
- Game theoretic analysis on machine learning models
- Misuse of AI and deep learning
Security and Privacy
- Detecting dataset anomalies that lead to autonomous system security and privacy violations
- Differential privacy and privacy-preserving learning and generative models
- Adversarial attacks on machine learning and defenses against adversarial attacks
- Attacks against deep learning and security of deep learning systems
- Theoretical foundations of machine learning security
- Formal verification of machine learning models and systems
- Define and understand AI vulnerabilities and exploitable bugs in ML systems
- Improve resiliency of AI methods and algorithms to various forms of attacks
Detailed submission information can be found on the workshop website: https://www.ieee-security.org/TC/SPW2020/WAAS/#submission
Submission Guidelines
- You are invited to submit regular papers of up to six pages, or four pages for works in progress, including references. To be considered, papers must be received by the submission deadline. Submissions must be original work and may not be under submission to another venue at the time of review. Please mark all of your conflicts of interest when submitting your paper.
- Papers must be formatted for US letter (not A4) size paper. The text must be formatted in a two-column layout, with columns no more than 9.5 in. tall and 3.5 in. wide. The text must be in Times font, 10-point or larger, with 11-point or larger line spacing. Authors are strongly recommended to use the latest IEEE conference proceedings templates. Failure to adhere to the page limit and formatting requirements are grounds for rejection without review.
Presentation Form
- All accepted submissions will be presented at the workshop and included in the IEEE workshop proceedings. Due to time constraints, accepted papers will be selected for presentation as either talk or poster based on their review score and novelty. Nonetheless, all accepted papers should be considered as having equal importance.
- One author of each accepted paper is required to attend the workshop and present the paper for it to be included in the proceedings.
Committee
- Workshop Chair
- Lanier Watkins, Johns Hopkins University & Applied Physics Lab
- Workshop Co-Chair
- Howard Shrobe, MIT Computer Science & Artificial Intelligence Lab
- Program Chair
- Chris Rouff, Johns Hopkins University Applied Physics Lab
- Program Co-Chair
- Reza Ghanadan, Google
- Program Committee
- Natalia Alexandrov, NASA Langley Research Center
- Yair Amir, Johns Hopkins University
- Saurabh Bagchi, Purdue University
- Raheem Beyah, Georgia Institute of Technology
- Yinzhi Cao, John Hopkins University
- Anupam Chattopadhyay, Singapore Nanyang Technological University
- Joel Coffman, United States Air Force Academy
- Misty Davies, NASA Ames Research Center
- David Doria, HERE Technologies
- Abhishek Dubey, Vanderbilt University
- Ashutosh Dutta, Johns Hopkins University Applied Physics Lab
- Mike Hinchey, University of Limerick
- Dezhi Hong, University of California San Diego
- Yan Huang, Indiana University
- John S. Hurley, National Defense University
- Avinash Kalyanaraman, University of Virginia
- Gabor Karsai, Vanderbilt University
- Mykel Kochenderfer, Stanford University
- Xenofon Koutsoukos, Vanderbilt University
- Jose A. Morales, Carnegie Mellon University
- Sirajum Munir, Bosch Research and Technology Center
- Jared Oluoch, University of Toledo
- William H. Robinson, Vanderbilt University
- Yasser Shoukry, University of Maryland
- Houbing Song, Embry-Riddle University
- Tamim Sookoor, Johns Hopkins University Applied Physics Lab
- Roy Sterritt, Ulster University
- Jeremy Straub, University of North Dakota
- A. Selcuk Uluagac, Florida International University
- Kristen Walcott, University of Colorado
- Louis Whitcomb, Johns Hopkins University
- Paul Wood, Johns Hopkins University Applied Physics Lab