Related papers: The Efficacy of SHIELD under Different Threat Mode…
Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the models from…
We show that when taking into account also the image domain $[0,1]^d$, established $l_1$-projected gradient descent (PGD) attacks are suboptimal as they do not consider that the effective threat model is the intersection of the $l_1$-ball…
Continual learning under adversarial conditions remains an open problem, as existing methods often compromise either robustness, scalability, or both. We propose a novel framework that integrates Interval Bound Propagation (IBP) with a…
Learned image compression (LIC) is becoming more and more popular these years with its high efficiency and outstanding compression quality. Still, the practicality against modified inputs added with specific noise could not be ignored.…
Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…
Designing powerful adversarial attacks is of paramount importance for the evaluation of $\ell_p$-bounded adversarial defenses. Projected Gradient Descent (PGD) is one of the most effective and conceptually simple algorithms to generate such…
Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Projected Gradient Descent (PGD) attack has been demonstrated to be one of the most successful adversarial attacks.…
Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an…
Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…
We experimented with front-end enhanced neural models where a differentiable and fully convolutional model with a skip connection is added before a frozen backbone classifier. By training such composite models using a small learning rate…
The increasing prevalence of adversarial attacks on Artificial Intelligence (AI) systems has created a need for innovative security measures. However, the current methods of defending against these attacks often come with a high computing…
State-of-the-art defense mechanisms are typically evaluated in the context of white-box attacks, which is not realistic, as it assumes the attacker can access the gradients of the target network. To protect against this scenario,…
Deep learning models have shown incredible performance on numerous image recognition, classification, and reconstruction tasks. Although very appealing and valuable due to their predictive capabilities, one common threat remains challenging…
Adversarial attacks on deep neural network models have seen rapid development and are extensively used to study the stability of these networks. Among various adversarial strategies, Projected Gradient Descent (PGD) is a widely adopted…
Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…
In this technical report, we evaluate the adversarial robustness of a very recent method called "Geometry-aware Instance-reweighted Adversarial Training"[7]. GAIRAT reports state-of-the-art results on defenses to adversarial attacks on the…
Deep neural network based medical image systems are vulnerable to adversarial examples. Many defense mechanisms have been proposed in the literature, however, the existing defenses assume a passive attacker who knows little about the…
We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demonstrated to outperform state-of-the-art defenses against…
Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g., adversarial training. Randomized smoothing, the averaging of…
Federated Learning (FL) has recently emerged as a revolutionary approach to collaborative training Machine Learning models. In particular, it enables decentralized model training while preserving data privacy, but its distributed nature…