33 citations · 54 across the 12 of their papers we have counts for
5 papers · 1 filter
Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
Tao Sun, Lu Pang, Weimin Lyu +2
Deep neural networks are vulnerable to backdoor attacks, where an adversary manipulates the model behavior through overlaying images with special triggers. Existing backdoor defens…
Backdoor Cleansing with Unlabeled Data
Lu Pang, Tao Sun, Haibin Ling +1
Due to the increasing computational demand of Deep Neural Networks (DNNs), companies and organizations have begun to outsource the training process. However, the externally trained…
Local Context-Aware Active Domain Adaptation
Tao Sun, Cheng Lu, Haibin Ling
Active Domain Adaptation (ADA) queries the labels of a small number of selected target samples to help adapting a model from a source domain to a target domain. The local context o…
Domain Adaptation with Adversarial Training on Penultimate Activations
Tao Sun, Cheng Lu, Haibin Ling
Enhancing model prediction confidence on target data is an important objective in Unsupervised Domain Adaptation (UDA). In this paper, we explore adversarial training on penultimat…
Prior Knowledge Guided Unsupervised Domain Adaptation
Tao Sun, Cheng Lu, Haibin Ling
The waive of labels in the target domain makes Unsupervised Domain Adaptation (UDA) an attractive technique in many real-world applications, though it also brings great challenges…