Workshop Agenda (virtual event): August 15th, 2021, 4-8 pm (US eastern time)

• 4-5 pm: Invited talk by Xue (Shelley) Lin: Secure Deep Learning – Adversarial T-shirt, Attack Detection, and Robust Ensemble

• 5-6 pm: AdvML 2021 Rising Star Awards & Presentations (sponsored by MIT-IBM Watson AI Lab)

  • Florian Tramer: Does Adversarial Machine Learning Research Matter?

  • Huan Zhang: Unboxing the Black-box: A Quest for Scalable and Powerful Neural Network Verifiers

• 6-7 pm: Presentations of Accepted Papers and Live Q&A

• 7-8 pm: Invited talk by Xiaoming Liu: On the Detection and Reverse Engineering of Diverse Attacks to Faces

• MIT-IBM Watson AI Lab best paper award: Vito Walter Anelli (Polytechnic University of Bari); Yashar Deldjoo (Polytechnic University of Bari); Tommaso Di Noia (Politecnico di Bari); Felice Antonio Merra (Politecnico di Bari). Understanding the Effects of Adversarial Personalized Ranking Optimization Method on Recommendation Quality

Accepted Papers:

• Vito Walter Anelli (Polytechnic University of Bari); Yashar Deldjoo (Polytechnic University of Bari); Tommaso Di Noia (Politecnico di Bari); Felice Antonio Merra (Politecnico di Bari). Understanding the Effects of Adversarial Personalized Ranking Optimization Method on Recommendation Quality [MIT IBM Watson AI Lab Best Paper Award]

• David Stutz (Max Planck Institute for Informatics); Matthias Hein (University of Tübingen); Bernt Schiele (MPI Informatics). Relating Adversarially Robust Generalization to Flat Minima

• David Stutz (Max Planck Institute for Informatics); Nandhini Chandramoorthy (IBM T. J. Watson Research Center); Matthias Hein (University of Tübingen); Bernt Schiele (MPI Informatics). Bit Error Robustness for Energy-Efficient DNN Accelerators

• Nimrah Shakeel. Context-Free Word Importance Scores for Attacking Neural Networks

• Jacob M Springer (Los Alamos National Laboratory); Bryn Reinstadler (MIT); Una-May O'Reilly (MIT). STRATA: Simple, Gradient-Free Attacks for Models of Code

• Clayton B Washington (The Ohio State University); Maximum Wilder-Smith (California State Polytechnic University at Pomona); Tingting Chen (California State Polytechnic University at Pomona); Hao Ji (California State Polytechnic University at Pomona). Robust Localized Physical Attacks on Deep Learning Classifiersfor Objects with Arbitrary Surface

• Ankita Shukla (Arizona State University); Pavan Turaga (Arizona State University); Saket Anand (Indraprastha Institute of Information Technology Delhi). Cleaning Adversarial Perturbations with Image-Subspace Projections

• Yize Li (Northeastern University); Pu Zhao (Northeastern University); Yao Yuguang (Michigan State University); Vishal Asnani (Michigan State University); Yifan Gong (Northeastern University); Yimeng Zhang (Michigan State University); Zhengang Li (Northeastern University); Xiaoming Liu (Michigan State University); Sijia Liu (Michigan State University); Xue Lin (Northeastern University). Supervised Classification on Deep Neural Network Attack Toolchains

• Chenan Wang (Northeastern University); Pu Zhao (Northeastern University); Siyue Wang (Northeastern University); Xue Lin (Northeastern University). Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning

• Gihyuk Ko (Carnegie Mellon University); Gyumin Lim (Korea Advanced Institute of Science and Technology). Unsupervised Detection of Adversarial Examples with Model Explanations

Call for Papers:

Topics of interest include but are not limited to:

• Adversarial attacks and defenses in machine learning and data mining

• Provably robust machine learning methods and systems

• Robustness certification and property verification techniques

• Representation learning, knowledge discovery and model generalizability

• Generative models and their applications (e.g., generative adversarial nets)

• Robust optimization methods and (computational) game theory

• Explainable and fair machine learning models via adversarial learning techniques

• Transfer learning, multi-agent adaptation, self-paced learning

• Privacy and security in machine learning systems

• Novel applications and innovations using adversarial machine learning and data mining