4th Workshop on Adversarial Learning Methods for Machine Learning and Data Mining @ KDD 2022
1:00 - 1:30 pm: Invited talk by Prof. SueYeon Chung on Neuro-inspired Mechanisms for Adversarial Robustness
1:30 - 2:00 pm: Invited talk by Prof. Soheil Feizi on A Conjecture on Optimal Robustness against Poisoning Attacks via Few-shot Learning
2:00 - 2:30 pm: Invited talk by Raman Arora on Guaranteed adversarially robust training of neural networks
2:30 - 3:00 pm: Panel discussion on Opportunities and Challenges for Adversarial Machine Learning
3:00 - 3:30 pm: Coffee Break and Poster Session #1
3:30 - 4 pm: Rising Star presentation by Fatemehsadat Mireshghallah on How much can we trust large language models?
4 - 4:30 pm: Rising Star presentation by Linyi Li on Enabling Certifiable Deep Learning for Large-Scale Models towards Real-World Requirements
4:30 - 5 pm: Best paper award presentation & Poster Session #2
Bon View Publishing Best Paper Award: Lei Xu (MIT); Laure Berti-Equille (IRD); Alfredo Cuesta Infante (Universidad Rey Juan Carlos); Kalyan Veeramachaneni (MIT). In Situ Augmentation for Defending Against Adversarial Attacks on Text Classifiers
We are happy to announce that Bon View Press will sponsor our best paper award with a 500 USD cash prize!
Accepted workshop papers now have the option to publish in the Journal of Computational and Cognitive Engineering with a fast-track review process!
Co-located conference: KDD 2022
Workshop Date and time: Aug. 15th (1-5 pm)
Organizers: Pin-Yu Chen (IBM Research), Cho-Jui Hsieh (UCLA), Bo Li (UIUC), SIjia Liu (Michigan State University)
Paper submission Deadline:
May 26th, 2022 (anywhere on earth)June 2nd, 2022 (anywhere on earth; final)Notification Date: June 20th, 2022
Submission Site: CMT
Paper submission format: ACM template (sample-sigconf), 4 pages excluding references and supporting materials in one single pdf file. The authors can choose to anonymize the author information during submission (but are not required to do so)
Call for AdvML Rising Star Award Nominations! (Due June 24th)
Accepted Papers:
Huang Dong (University of Hong Kong); Bu Qingwen (The University of Hong Kong); Yuhao Qing (The University of Hong Kong); Haowen Pi (The University of Hong Kong); Heming Cui (The University of Hong Kong). NAGen: Adversarial Training with Neuron-Aware Adversarial Example Generation
Hari Prasanna Das (UC Berkeley ); Ryan Tran (UC Berkeley); Japjot Singh (UC Berkeley); Yu Wen Lin (UC Berkeley); Costas J. Spanos (University of California at Berkeley). Unsupervised Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training
Lei Xu (MIT); Laure Berti-Equille (IRD); Alfredo Cuesta Infante (Universidad Rey Juan Carlos); Kalyan Veeramachaneni (MIT). In Situ Augmentation for Defending Against Adversarial Attacks on Text Classifiers [Bon View Publishing Best Paper Award]
Sandipan Choudhuri (Arizona State University); Hemanth Venkateswara (Arizona State University); Arunabha Sen (Arizona State University). Coupling Adversarial Learning with Selective Voting Strategy for Distribution Alignment in Partial Domain Adaptation
Carmelo Ardito (Polytechnic University of Bari); Yashar Deldjoo (Polytechnic University of Bari); Tommaso Di Noia (Polytechnic University of Bari); Eugenio Di Sciascio (Politecnico di Bari); Fatemeh Nazary (Politecnico di Bari); Giovanni Servedio (Polytechnic University of Bari). Machine-learned Adversarial Attacks against Fault Prediction Systems in Smart Electrical Grids
Scott R Oslund (University of California, Santa Cruz); Clayton B Washington (The Ohio State University); Andrew So (California State Polytechnic University at Pomona); Tingting Chen (California State Polytechnic University at Pomona); Hao Ji (California State Polytechnic University at Pomona). Robust Adversarial Stickers for Arbitrary Objects in the Physical World
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
Adversarial machine learning for (social) good
Novel applications and innovations using adversarial machine learning and data mining
Organizers:
Pin-Yu Chen (IBM Research), Cho-Jui Hsieh (UCLA), Bo Li (UIUC), Sijia Liu (Michigan State University)