TL;DR
The obtained results exhibit the efficacy of the multi-teacher adversarial distillation and adaptive learning strategy, enhancing CNNs’ adversarial robustness against various adversarial attacks.
This work introduces Oscillatory Predictive Learning (OPL), a two-stage framework that combines Artificial Kuramoto Oscillatory Neurons (AKOrN) with predictive self-supervised pretraining using X-PhiNet and compares it with other randomized adversarial defense methods that provide precise, reproducible, and strong atta...
RL-FAT is proposed, a reinforcement-learning-inspired fair adversarial training framework that uses policy-gradient based feedback from adversarial predictions to improve adversarial robustness while promoting a more balanced robustness distribution across classes.
This work proposes a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model, and shows the success of reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial...
Adversarial training, one of the most effective methods for enhancing neural network robustness, is typically formulated as a min-max game between an attacker and a defender. Despite its success, most adversarial training methods suffer from robust overfitting, leading to a significant gap in robustness between the tra...
This work explores different neural network architectures, including fully connected networks, classical convolutional networks, and residual networks, under four types of adversarial attacks constrained by different L p norms, and investigates how adversarial examples affect the internal representations of networks...
The defense effect of GVAT was generalized to other attacks under the transfer-based black-box setting, which showed that GVAT not only defended against the corresponding attacks that generated adversarial examples but also defended against other attacks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
