相关论文: Towards adversarial robustness with 01 loss neural…

White box adversarial perturbations are sought via iterative optimization algorithms most often minimizing an adversarial loss on a $l_p$ neighborhood of the original image, the so-called distortion set. Constraining the adversarial search…

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate…

We propose a new, simple framework for crafting adversarial examples for black box attacks. The idea is to simulate the substitution model with a non-trainable model compounded of just one layer of handcrafted convolutional kernels and then…

We analyze the properties of adversarial training for learning adversarially robust halfspaces in the presence of agnostic label noise. Denoting $\mathsf{OPT}_{p,r}$ as the best robust classification error achieved by a halfspace that is…

With the rise of powerful foundation models, a pre-training-fine-tuning paradigm becomes increasingly popular these days: A foundation model is pre-trained using a huge amount of data from various sources, and then the downstream users only…

Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-designed, small perturbations at the input layer, or so-called adversarial examples. Taking images as an example, such distortions are often imperceptible,…

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance…

Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to adversarial attacks poses a serious security risk. Progress in defending these models…

Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of this sensitivity is not well understood, theoretical…

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in…

Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is…

Deep neural networks (DNNs) are vulnerable to malicious inputs crafted by an adversary to produce erroneous outputs. Works on securing neural networks against adversarial examples achieve high empirical robustness on simple datasets such as…

Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to…

Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the benchmark of model robustness. Existing benchmarks mainly focus on evaluating defenses, but there are no comprehensive studies of how architecture design…

Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce drastically different outputs. Many defense methods require…

Deep learning models have proven to be successful in a wide range of machine learning tasks. Yet, they are often highly sensitive to perturbations on the input data which can lead to incorrect decisions with high confidence, hampering their…

In this paper, we present a novel nonlinear programming-based approach to fine-tune pre-trained neural networks to improve robustness against adversarial attacks while maintaining high accuracy on clean data. Our method introduces…

In the context of adversarial robustness, a single model does not usually have enough power to defend against all possible adversarial attacks, and as a result, has sub-optimal robustness. Consequently, an emerging line of work has focused…

Adversarial training (AT) incurs significant computational overhead, leading to growing interest in designing inherently robust architectures. We demonstrate that a carefully designed first layer of the neural network can serve as an…