Achieving Adversarial Robustness Requires An Active Teacher
A new understanding of adversarial examples and adversarial robustness is proposed by decoupling the data generator and the label generator (which we call the teacher). In our framework, adversarial robustness is a conditional concept---the student model is not absolutely robust, but robust with respect to the teacher. Based on the new understanding, we claim that adversarial examples exist because the student cannot obtain sufficient information of the teacher from the training data. Various ways of achieving robustness is compared. Theoretical and numerical evidence shows that to efficiently attain robustness, a teacher that actively provides its information to the student may be necessary.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation
Adversarial Training is a practical approach for improving the robustness of deep neural networks against adversarial attacks. Although bringing reliable robustness, the performance towards clean examples is negatively a…
Adversarial RobustnessKnowledge DistillationDistilling Adversarial Robustness Using Heterogeneous Teachers
Achieving resiliency against adversarial attacks is necessary prior to deploying neural network classifiers in domains where misclassification incurs substantial costs, e.g., self-driving cars or medical imaging. Recent …
Adversarial RobustnessKnowledge DistillationSelf-Driving CarsAdversarial Training via Adaptive Knowledge Amalgamation of an Ensemble of Teachers
Adversarial training (AT) is a popular method for training robust deep neural networks (DNNs) against adversarial attacks. Yet, AT suffers from two shortcomings: (i) the robustness of DNNs trained by AT is highly intertw…
Adversarial RobustnessExponential Separation between Two Learning Models and Adversarial Robustness
We prove an exponential separation for the sample/query complexity between the standard PAC-learning model and a version of the Equivalence-Query-learning model. In the PAC model all samples are provided at the beginning…
Adversarial RobustnessPAC learningVocal Bursts Valence PredictionMMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models
Vision-Language Models (VLMs) are increasingly deployed in safety-critical applications, making their adversarial robustness a crucial concern. While adversarial knowledge distillation has shown promise in transferring r…
Adversarial RobustnessKnowledge Distillation