Towards Adversarial Robustness via Transductive Learning
There has been emerging interest to use transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020). Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain" the model based on test time input via transductive learning; and theoretically, attacking these defenses boils down to bilevel optimization, which seems to raise the difficulty for adaptive attacks. In this paper, we first formalize and analyze modeling aspects of transductive robustness. Then, we propose the principle of attacking model space for solving bilevel attack objectives, and present an instantiation of the principle which breaks previous transductive defenses. These attacks thus point to significant difficulties in the use of transductive learning to improve adversarial robustness. To this end, we present new theoretical and empirical evidence in support of the utility of transductive learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessBilevel OptimizationTransductive LearningSimilar Papers 제목 키워드 기반
Towards Evaluating the Robustness of Neural Networks Learned by Transduction
There has been emerging interest in using transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020; Wang et al., ArXiv 2021). Compared to traditional defenses, these defense…
Adversarial RobustnessBilevel OptimizationTransductive LearningTowards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks
Graph neural networks (GNNs) have recently been shown to be vulnerable to adversarial attacks, where slight perturbations in the graph structure can lead to erroneous predictions. However, current robust models for defen…
TransductGAN: a Transductive Adversarial Model for Novelty Detection
Novelty detection, a widely studied problem in machine learning, is the problem of detecting a novel class of data that has not been previously observed. A common setting for novelty detection is inductive whereby only e…
Generative Adversarial NetworkmodelNovelty DetectionOut-of-Distribution DetectionTransductive Robust Learning Guarantees
We study the problem of adversarially robust learning in the transductive setting. For classes $\mathcal{H}$ of bounded VC dimension, we propose a simple transductive learner that when presented with a set of labeled tra…
Transductive Adversarial Networks (TAN)
Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also…
Domain Adaptation