Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off
While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy. This has led to prior works postulating that accuracy is inherently at odds with robustness. Yet, the phenomenon remains inexplicable. In this paper, we closely examine the changes induced in the decision boundary of a deep network during adversarial training. We find that adversarial training leads to unwarranted increase in the margin along certain adversarial directions, thereby hurting accuracy. Motivated by this observation, we present a novel algorithm, called Helper-based Adversarial Training (HAT), to reduce this effect by incorporating additional wrongly labelled examples during training. Our proposed method provides a notable improvement in accuracy without compromising robustness. It achieves a better trade-off between accuracy and robustness in comparison to existing defenses.
Code (2)
Tasks
Adversarial DefenseAdversarial RobustnessRobust classificationSimilar Papers 제목 키워드 기반
Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off
While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy. This has led to prior works postulating that accuracy is inherently at odds with robustness. Ye…
Self-Regulation and Requesting Interventions
Human intelligence involves metacognitive abilities like self-regulation, recognizing limitations, and seeking assistance only when needed. While LLM Agents excel in many domains, they often lack this awareness. Overconf…
Workflow Optimization for Parallel Split Learning
Split learning (SL) has been recently proposed as a way to enable resource-constrained devices to train multi-parameter neural networks (NNs) and participate in federated learning (FL). In a nutshell, SL splits the NN mo…
Federated LearningSchedulingFINED: Fast Inference Network for Edge Detection
In this paper, we address the design of lightweight deep learning-based edge detection. The deep learning technology offers a significant improvement on the edge detection accuracy. However, typical neural network design…
Deep LearningEdge DetectionObject DetectionSemantic SegmentationIncreasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks
Deep neural networks (DNNs) are vulnerable to adversarial noises. By adding adversarial noises to training samples, adversarial training can improve the model's robustness against adversarial noises. However, adversarial…
Adversarial RobustnessGeneral ClassificationImage ClassificationImage Segmentation+3