Call for Submissions

This workshop will bring classical system architecture and design experts and AI/ML algorithmic experts together in one forum. The goal is to brainstorm about challenges in designing secure and resilient AI-centric systems in general, but with a special focus on autonomous systems (such as self-driving cars and industrial robots) – where safety and security are of paramount value.

The knowledge and expertise of classical mainframe and server architects who are experts in designing ultra-reliable and secure systems will be blended with domain experts in AI; particularly those with an established expertise in developing reliable and secure AI algorithms.

The organizers of this workshop largely represent the classical system architects with expertise in building robust and energy efficient systems. The program will be a blend of talks selected from submitted abstracts and invited speakers. The latter will largely feature experts in core AI algorithms, especially those focused on adversarial robustness, few-shot learning, immunity against catastrophic forgetfulness, etc.

Call for Presentation Abstracts

This first workshop on SARA (Secure and Resilient Autonomy) will primarily focus on the safety, security and reliability aspects of AI-centric systems. Topics of interest include (but are not limited to):

  • Resilience and security considerations in emerging new domains such as autonomous vehicles, cognitive IoT swarms, as well as existing server-class and embedded architectures for the AI and machine learning applications.
  • Anomaly detection in AI-centric systems.
  • Error and threat models; associated vulnerability assessment metrics.
  • Design of secure and robust cloud-backed edge-architectures for machine learning applications.
  • Algorithmic techniques to improve training and inference in the presence of errors.
  • Hardware-software co-design of resilient machine learning systems.
  • Characterization of hardware and system-level vulnerabilities resulting in unplanned failures and/or adversarial attacks.
  • End-to-end resilience evaluation of real machine learning systems.
  • Resilient design of distributed swarm-based architectures for machine learning.
  • Lifelong learning, few-shot learning and mitigation of catastrophic forgetfulness.
  • Energy efficiency and endurance in mobile and embedded AI architectures.

Researchers in this field are encouraged to submit an extended abstract. We also encourage presentations showcasing prototype demonstrations and open source contributions.

Submission site:

If you have questions regarding submission, please contact us:

Important Dates

  • Submission of presentation abstracts: January 15th 2020 January 19th 2020 (deadline extended).
  • Notification of acceptance: February 6th 2020.
  • Final 2-page (max) paper due (for inclusion in online proceedings): February 24th 2020.
  • Workshop date: March 4th 2020.

Workshop Organization and Planning

The workshop organizing committee has put together a program committee that will assist in selecting papers (abstracts) submitted to SARA. The program committee member names will be published online within the next couple of weeks.


  1. Video recording of talks and paper proceedings will be made available on the website after the workshop.
  2. Post-workshop special issues in AI Magazine and/or IEEE Micro Magazine. (These are pending proposals, likely to be accepted).

Program Committee

  • Dr. Saibal Mukhopadhyay, Georgia Institute of Technology
  • Dr. Gabriel Silva, University of California San Diego
  • Dr. Subhasish Mitra, Stanford University
  • Dr. Sijia Liu, MIT-IBM Watson AI Lab
  • Dr. Pin-Yu Chen, IBM Research
  • Dr. Sarita Adve, University of Illinois Urbana-Champaign
  • Dr. Sanu Mathew, Intel
  • Dr. Karthik Pattabiraman, The University of British Columbia

Abstract Submission Deadline
January 19th 2020

February 6th 2020

Workshop date
March 4th 2020

Program (Wednesday March 4th, 2020)

Time (CT) Talk Title Talk Category Speaker(s)
9:00am Workshop Introduction Welcoming Remarks Nandhini Chandramoorthy (IBM)
9:05am Secure and Resilient — a DARPA View Keynote-I Dr. Tom Rondeau (DARPA MTO)
9:50am Coffee Break + Discussion
Morning Paper and Invited Talk Session: Chair – Karthik Swaminathan (IBM)
10:05am Energy-Efficient Circuits for Entropy Generation and Secure Encryption Invited Talk-I Dr. Sanu Matthew (Intel Corp.)
10:25am Feature Map Vulnerability Evaluation in CNNs    Accepted Paper Abdulrahman Mahmoud (UIUC), Siva Kumar Sastry Hari (NVIDIA), Christopher Fletcher (UIUC), Sarita Adve (UIUC), Charbel Sakr (UIUC), Naresh Shanbag (UIUC), Pavlo Molchanov (NVIDIA), Michael Sullivan (NVIDIA), Timothy Tsai (NVIDIA), Stephen Keckler (NVIDIA)
10:40am Reliable Intelligence in Unreliable Environment Invited Talk-II Dr. Saibal Mukhopadhyay (GeorgiaTech)
11:00am Towards Information Theoretic Adversarial Examples    Accepted Paper Chia-Yi Hsu (NCHU), Pin-Yu Chen (IBM), Chia-Mu Yu (NCHU)
11:15am Explaining Away Attacks against Neural Networks    Accepted Paper Sean Saito, Jin Wang (SAP Asia)
11:30am Poster Presentations + Discussion
12:00pm Lunch Break
1:30pm Poster Presentations + Discussion (contd.)
2:00pm Towards Robust and Efficient Deep Learning Systems Keynote-II Prof. Xue Lin (Northeastern University)
Afternoon Paper and Invited Talk Session
2:45pm MUTE: Data-Similarity Driven Multi-Hot Target Encoding for Neural Network Design    Accepted Paper Mayoore Jaiswal, Bumsoo Kang, Jinho Lee, Minsik Cho (IBM)
3:00pm WARDEN: Warranting Robustness against Deception in Data Centers    Accepted Paper Hazar Yueksel, Ramon Bertran, Alper Buyuktosunoglu (IBM)
3:15pm Self-Progressing Robust Training Embedded Tutorial (Invited Talk-III) Dr. Pin-Yu Chen (IBM)
3:45pm Coffee Break + Discussion
4:00pm Panel Session: Pin-Yu Chen (IBM), Xue Lin (Northeastern University), Akshay Deshpande (Soothsayer Analytics), Sean Saito (SAP Asia).
Moderators: Nandhini Chandramoorthy, Pradip Bose (IBM)
5:00pm Conclusion Closing Remarks Organizers (IBM)


Pradip Bose is a Distinguished Research Staff Member and manager of Efficient and Resilient Systems at IBM T. J. Watson Research Center. He has over thirty-six years of experience at IBM, and was a member of the pioneering RISC super scalar project at IBM (a pre-cursor to the first RS/6000 system product). He holds a Ph.D. degree from University of Illinois at Urbana-Champaign.

Nandhini Chandramoorthy is a Research Staff Member at IBM T. J. Watson Research Center involved in Deep Neural Network ASIC design with techniques to improve reliable operation at very low supply voltages, and pre-RTL performance modeling tools for multi-core architectures. She holds a Ph.D. degree from Penn State University.

Augusto Vega is a Research Staff Member at IBM T. J. Watson Research Center involved in research and development work in the areas of highly-reliable power-efficient embedded designs, cognitive systems and mobile computing. He holds a Ph.D. degree from Polytechnic University of Catalonia (UPC), Spain.

Karthik Swaminathan is a Research Staff Member at IBM T. J. Watson Research Center. His research interests include power and resilience-aware architectures, domain-specific accelerators and emerging technologies in processor design. He is also interested in aspects related to reliability and energy efficiency, particularly in architectures for machine learning. He holds a Ph.D. degree from Penn State University.


SARA will be held in conjunction with the Third Conference on Machine Learning and Systems (MLSys). Refer to the main venue to continue with the registration process.

Event Location

Austin Convention Center
500 E Cesar Chavez St
Austin, TX 78701

Check main conference site for venue information.