CAT: Customized Adversarial Training for Improved Robustness
Adversarial training has become one of the most effective methods for improving robustness of neural networks. However, it often suffers from poor generalization on both clean and perturbed data. In this paper, we propose a new algorithm, named Customized Adversarial Training (CAT), which adaptively customizes the perturbation level and the corresponding label for each training sample in adversarial training. We show that the proposed algorithm achieves better clean and robust accuracy than previous adversarial training methods through extensive experiments.
Code (1)
Similar Papers 제목 키워드 기반
Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracy
Randomized smoothing (RS) is an effective and scalable technique for constructing neural network classifiers that are certifiably robust to adversarial perturbations. Most RS works focus on training a good base model tha…
Is ReLU Adversarially Robust?
The efficacy of deep learning models has been called into question by the presence of adversarial examples. Addressing the vulnerability of deep learning models to adversarial examples is crucial for ensuring their conti…
Deep LearningPrompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
Diffusion models have revolutionized customized text-to-image generation, allowing for efficient synthesis of photos from personal data with textual descriptions. However, these advancements bring forth risks including p…
Image GenerationText to Image GenerationText-to-Image GenerationGame Theoretic Mixed Experts for Combinational Adversarial Machine Learning
Recent advances in adversarial machine learning have shown that defenses considered to be robust are actually susceptible to adversarial attacks which are specifically customized to target their weaknesses. These defense…
Adversarial DefenseMMARD: Improving the Min-Max Optimization Process in Adversarial Robustness Distillation
Adversarial Robustness Distillation (ARD) is a promising task to boost the robustness of small-capacity models with the guidance of the pre-trained robust teacher. The ARD can be summarized as a min-max optimization proc…
Adversarial Robustness