相关论文: Scaling Compute Is Not All You Need for Adversaria…

Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the…

This paper revisits the simple, long-studied, yet still unsolved problem of making image classifiers robust to imperceptible perturbations. Taking CIFAR10 as an example, SOTA clean accuracy is about $100$%, but SOTA robustness to…

While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…

While many defences against adversarial examples have been proposed, finding robust machine learning models is still an open problem. The most compelling defence to date is adversarial training and consists of complementing the training…

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce…

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks. In this…

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their…

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on reducing robust overfitting by using common data augmentation schemes. We…

Adversarial training has been actively studied in recent computer vision research to improve the robustness of models. However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often…

Pretrained models from self-supervision are prevalently used in fine-tuning downstream tasks faster or for better accuracy. However, gaining robustness from pretraining is left unexplored. We introduce adversarial training into…

Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real…

Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt generalization performance…

Recently, RobustBench (Croce et al. 2020) has become a widely recognized benchmark for the adversarial robustness of image classification networks. In its most commonly reported sub-task, RobustBench evaluates and ranks the adversarial…

Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-the-art vision models…

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…

Despite its popularity, deep neural networks are easily fooled. To alleviate this deficiency, researchers are actively developing new training strategies, which encourage models that are robust to small input perturbations. Several…

As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications.One effective way to improve the security of deep…