相关论文: Sparse and Transferable Universal Singular Vectors…

Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…

We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well recognized mode collapse. We first proceed by mapping the desired data onto a…

In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the limited feedback…

It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks (DNNs). In this paper, we make the case that sparse representations of the input data are a crucial tool for combating…

State-of-the-art deep neural networks have been shown to be extremely powerful in a variety of perceptual tasks like semantic segmentation. However, these networks are vulnerable to adversarial perturbations of the input which are…

Adversarial perturbations can deceive neural networks by adding small, imperceptible noise to the input. Recent object trackers with transformer backbones have shown strong performance on tracking datasets, but their adversarial robustness…

Adversarial examples reveal the blind spots of deep neural networks (DNNs) and represent a major concern for security-critical applications. The transferability of adversarial examples makes real-world attacks possible in black-box…

In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored. We propose an adversarial attack strategy on videos, called DeepSAVA. Our…

In this work, we highlight and perform a comprehensive study on calibration attacks, a form of adversarial attacks that aim to trap victim models to be heavily miscalibrated without altering their predicted labels, hence endangering the…

Sparse and patch adversarial attacks were previously shown to be applicable in realistic settings and are considered a security risk to autonomous systems. Sparse adversarial perturbations constitute a setting in which the adversarial…

Adversarial attacks on face recognition (FR) systems pose a significant security threat, yet most are confined to the digital domain or require white-box access. We introduce GaP (Gaussian Patch), a novel method to generate a universal,…

Existing adversarial attacks often neglect perturbation sparsity, limiting their ability to model structural changes and to explain how deep neural networks (DNNs) process meaningful input patterns. We propose ATOS (Attack Through…

Gait recognition is widely used in social security applications due to its advantages in long-distance human identification. Recently, sequence-based methods have achieved high accuracy by learning abundant temporal and spatial information.…

Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on transfer learning has found that it is vulnerable to various…

Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of pre-trained models. However, black-box attacks often suffer…

Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which has raised security…

Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these works do not accurately…

Adversarial transferability remains a critical challenge in evaluating the robustness of deep neural networks. In security-critical applications, transferability enables black-box attacks without access to model internals, making it a key…

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure…

Universal adversarial perturbation attacks are widely used to analyze image classifiers that employ convolutional neural networks. Nowadays, some attacks can deceive image- and video-quality metrics. So sustainability analysis of these…