207 citations · 1.1k across the 49 of their papers we have counts for
5 papers · 1 filter
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff
Eitan Borgnia, Valeriia Cherepanova, Liam Fowl +5
Data poisoning and backdoor attacks manipulate victim models by maliciously modifying training data. In light of this growing threat, a recent survey of industry professionals reve…
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
Jonas Geiping, Liam Fowl, W. Ronny Huang +4
Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification…
Fast Convex Relaxations using Graph Discretizations
Jonas Geiping, Fjedor Gaede, Hartmut Bauermeister +1
Matching and partitioning problems are fundamentals of computer vision applications with examples in multilabel segmentation, stereo estimation and optical-flow computation. These…
MetaPoison: Practical General-purpose Clean-label Data Poisoning
W. Ronny Huang, Jonas Geiping, Liam Fowl +2
Data poisoning -- the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data -- is an emerging threat in the context…
Inverting Gradients -- How easy is it to break privacy in federated learning?
Jonas Geiping, Hartmut Bauermeister, Hannah Dröge +1
The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates…