SARA: Secure and Resilient Autonomy
Pradip Bose · Nandhini Chandramoorthy · Augusto Vega · Karthik Swaminathan

Wed Mar 4th 09:00 AM -- 05:30 PM @ Level 1 Room 3
Event URL: »

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.

Detailed workshop information, abstract submission instructions, dates:

09:00 AM Introduction: Nandhini Chandramoorthy (IBM) (Welcoming Remarks)
09:05 AM Keynote I: Dr. Thomas Rondeau (DARPA): Secure and Resilient - a DARPA View (Keynote presentation)
09:50 AM Coffee Break + Discussion (Break)
10:05 AM Energy-Efficient Circuits for Entropy Generation and Secure Encryption: Dr. Sanu Matthew (Intel Corp) (Invited Talk)
10:25 AM Feature Map Vulnerability Evaluation in CNNs: Abdulrahman Mahmoud, Siva Kumar Sastry Hari, Christopher W. Fletcher, Charbel Sakr, Naresh Shanbag, Pavlo Molchanov, Michael B. Sullivan,Timothy Tsai, Stephen W. Keckler (UIUC and NVIDIA co-authors) (Regular Presentation)
10:40 AM Reliable Intelligence in Unreliable Environment: Prof. Saibal Mukhopadhyay (Georgia Tech) (Invited Talk)
11:00 AM Towards Information Theoretic Adversarial Examples: Chia-Yi Hsu (NCHU), Pin-Yu Chen (IBM) and Chia-Mu Yu (NCHU) (Regular Presentation)
11:15 AM Explaining Away Attacks Against Neural Networks: Sean Saito, Jin Wang (SAP Asia) (Regular Presentation)
11:30 AM Poster Session + Discussion (Poster session)
12:00 PM Lunch Break (Break)
01:30 PM Poster Session + Discussion (Contd.) (Poster session)
02:00 PM Keynote II: Prof. Xue Lin (Northeastern University): Towards Robust and Efficient Deep Learning Systems (Keynote presentation)
02:45 PM MUTE: Data-Similarity Driven Multi-Hot Target Encoding for Neural Network Design: Mayoore Jaiswal, Bumsoo Kang, Jinho Lee, Minsik Cho (IBM) (Regular Presentation)
03:00 PM WARDEN: Warranting Robustness Against Deception in Data Centers: Hazar Yueksel, Ramon Bertran, Alper Buyuktosunoglu (IBM) (Regular Presentation)
03:15 PM Embedded Tutorial: Self-Progressing Robust Training; Dr. Pin-Yu Chen (IBM Corp) (Tutorial)
03:45 PM Coffee Break + Discussion (Break)
04:00 PM Panel Discussion: Pin-Yu Chen (IBM), Akshay Deshpande (Soothsayer Analytics), Xue Lin (Northeastern University); Sean Saito (SAP, Asia); Moderators: Dr. Nandhini Chandramoorthy and Dr. Pradip Bose (IBM) (Panel)
05:00 PM Closing Remarks: Organizers (IBM) (Conclusion)

Author Information

Pradip Bose (IBM T. J. Watson Research Center)
Nandhini Chandramoorthy (IBM T. J. Watson Research Center)
Augusto Vega (IBM Research)
Karthik Swaminathan (IBM Research)