2nd Workshop on Adversarial Learning Methods for Machine Learning and Data Mining @ KDD 2020 (virtual workshop)
Workshop Agenda (virtual event + Youtube broadcast): August 24th, 2020, 8 am to noon (US pacific time)
8-9 am: Invited talk by Una-May O'Reilly: Artificial Adversarial Intelligence
9-10 am: Invited talk by Kamalika Chaudhuri: The Mysteries of Adversarial Robustness for Non-parametric Methods
10-11 am: Invited talk by Quanquan Gu: Understanding, Improving and Evaluating Adversarial Robustness in Deep Learning <Slides>
11 am-noon: Best paper presentations + Virtual poster sessions
11:00 to 11:20 am: MIT-IBM Watson AI Lab best paper award: On Intrinsic Dataset Properties for Adversarial Machine Learning. Jeffrey Pan and Nicholas Zufelt
11:20 am to 11:35 am: MIT-IBM Watson AI Lab best paper award: Deep Partition Aggregation: Provable Defense against General Poisoning Attacks. Alexander Levine and Soheil Feizi
11:35 am to noon: breakout session via Zoom
MIT-IBM Watson AI Lab best paper award: Robustness to large-step adversarial manipulations for a subset of features. Aradhana Sinha, Amer Sinha, Ben Packer, Xuezhi Wang, Nithum Thain, Corey Lane, Ed Chi, Alex Beutel and Jilin Chen
Two Best Paper Awards and One Best Presentation Award are sponsored by MIT-IBM Watson AI Lab with cash prizes ($500 each)!
Co-located conference: KDD 2020
Workshop Date and time: August 24th, 2020, 8 am to noon (pacific time)
Organizers: Pin-Yu Chen (IBM Research), Cho-Jui Hsieh (UCLA), Bo Li (UIUC), SIjia Liu (IBM Research)
Paper submission Deadline:
May 20th, 2020June 20th, 2020 (due to COVID-19)Notification Date:
June 15th, 2020July 15th, 2020 (due to COVID-19)Submission Site: EasyChair
Paper submission format: ACM template, 4 pages excluding references and supporting materials. The authors can choose to anonymize the author information during submission (but not required to do so).
Accepted Papers:
Robust Variational Autoencoders: Generating Noise-Free Images from Corrupted Images. Huimin Ren, Yun Yue, Chong Zhou, Randy Paffenroth, Yanhua Li and Matthew Weiss
Improving the Adversarial Robustness of Transfer Learning via Noisy Feature Distillation. Ting-Wu Chin, Cha Zhang and Diana Marculescu
PareCO: Pareto-aware Channel Optimization for Slimmable Neural Networks. Ting-Wu Chin, Ari Morcos and Diana Marculescu
On Intrinsic Dataset Properties for Adversarial Machine Learning. Jeffrey Pan and Nicholas Zufelt [MIT-IBM Watson AI Lab best paper award]
Robustness to large-step adversarial manipulations for a subset of features. Aradhana Sinha, Amer Sinha, Ben Packer, Xuezhi Wang, Nithum Thain, Corey Lane, Ed Chi, Alex Beutel and Jilin Chen [MIT-IBM Watson AI Lab best presentation award]
Evaluation Indicator for Model Inversion Attack. Hiroaki Tanaka, Wataru Yamada, Keiichi Ochiai, Rina Okada, Satoshi Hasegawa and Daizo Ikeda
Improving LIME Robustness with Smarter Locality Sampling. Sean Saito, Eugene Chua, Nicholas Capel and Rocco Hu
Garment Design with Generative Adversarial Networks. Chenxi Yuan and Mohsen Moghaddam
Identifying Audio Adversarial Examples via Anomalous Pattern Detection. Victor Akinwande, Celia Cintas, Skyler Speakman and Srihari Sridharan
Is Robust Neurons’ Activation Sufficient to Robustify CNNs against Adversarial Attacks? Jingkang Wang, Gaoyuan Zhang and Sijia Liu
Deep Partition Aggregation: Provable Defense against General Poisoning Attacks. Alexander Levine and Soheil Feizi [MIT-IBM Watson AI Lab best paper award]
Topics of interest include but are not limited to:
Adversarial attacks (e.g. evasion, poison and model inversion) and defenses in machine learning and data mining
Robustness certification and property verification techniques
Representation learning, knowledge discovery and model generalizability
Model robustness against model compression (e.g. network pruning and quantization)
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
Trustworthy data mining and machine learning