相关论文: Adversarial defense based on distribution transfer

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…

In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial attacks and…

Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…

Deep neural networks (DNNs) are vulnerable to adversarial perturbation, where an imperceptible perturbation is added to the image that can fool the DNNs. Diffusion-based adversarial purification focuses on using the diffusion model to…

By injecting adversarial examples into training data, adversarial training is promising for improving the robustness of deep learning models. However, most existing adversarial training approaches are based on a specific type of adversarial…

Stability analysis is an essential aspect of studying the generalization ability of deep learning, as it involves deriving generalization bounds for stochastic gradient descent-based training algorithms. Adversarial training is the most…

Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target…

Despite recent advances in video action recognition achieving strong performance on existing benchmarks, these models often lack robustness when faced with natural distribution shifts between training and test data. We propose two novel…

Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is…

Adversarial examples, or nearly indistinguishable inputs created by an attacker, significantly reduce machine learning accuracy. Theoretical evidence has shown that the high intrinsic dimensionality of datasets facilitates an adversary's…

Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN),…

Recent findings suggest that diffusion models significantly enhance empirical adversarial robustness. While some intuitive explanations have been proposed, the precise mechanisms underlying these improvements remain unclear. In this work,…

Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial…

There has been emerging interest to use transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020). Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain"…

The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. The ability to successfully evade unseen models represents an…

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to…

While additional training data improves the robustness of deep neural networks against adversarial examples, it presents the challenge of curating a large number of specific real-world samples. We circumvent this challenge by using…

Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically misleading the DNNs.…

Transferability of adversarial examples is a key issue to apply this kind of attacks against multimedia forensics (MMF) techniques based on Deep Learning (DL) in a real-life setting. Adversarial example transferability, in fact, would open…

Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised…