Poster

Mon 17:00

Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks
Alexander Levine · Soheil Feizi

Poster

Wed 9:00

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
Jonas Geiping · Liam H Fowl · Ronny Huang · Wojciech Czaja · Gavin Taylor · Michael Moeller · Tom Goldstein

Poster

Tue 9:00

Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics
Yanchao Sun · Da Huo · Furong Huang

Workshop

Does Differential Privacy Defeat Data Poisoning?
Matthew Jagielski · Alina Oprea

Workshop

Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers
Clayton C Ashcraft

Workshop

Poisoned classifiers are not only backdoored, they are fundamentally broken
Mingjie Sun · Mingjie Sun · Siddhant Agarwal · Zico Kolter

Workshop

Adversarial Examples Make Stronger Poisons
Liam H Fowl · Micah Goldblum · Ping-yeh Chiang · Jonas Geiping · Tom Goldstein

Workshop

What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors
Jonas Geiping · Liam H Fowl · Micah Goldblum · Michael Moeller · Tom Goldstein

Workshop

Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
Javier Carnerero-Cano

Workshop

Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release
Liam H Fowl · Ping-yeh Chiang · Micah Goldblum · Jonas Geiping · Tom Goldstein

Workshop