相关论文: Improving Robustness to Model Inversion Attacks vi…

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks: carefully constructed perturbations to an image can seriously impair classification accuracy, while being imperceptible to humans. While there has been a significant amount…

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

To defend deep neural networks from adversarial attacks, adversarial training has been drawing increasing attention for its effectiveness. However, the accuracy and robustness resulting from the adversarial training are limited by the…

Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform…

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain…

Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a…

Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an attack crafted on a…

Adversarial robustness of deep models is pivotal in ensuring safe deployment in real world settings, but most modern defenses have narrow scope and expensive costs. In this paper, we propose a self-supervised method to detect adversarial…

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Memristive crossbars have become a popular means for realizing unsupervised and supervised learning techniques. In previous neuromorphic architectures with leaky integrate-and-fire neurons, the crossbar itself has been separated from the…

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to exploit intrinsic prior knowledge about the unknown…

Sparse coding networks, which utilize unsupervised learning to maximize coding efficiency, have successfully reproduced response properties found in primary visual cortex \cite{AN:OlshausenField96}. However, conventional sparse coding…

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Deep hashing improves retrieval efficiency through compact binary codes, yet it introduces severe and often overlooked privacy risks. The ability to reconstruct original training data from hash codes could lead to serious threats such as…

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the privacy vulnerabilities of Deep Neural Networks (DNNs).…

Sparse adversarial attacks can fool deep neural networks (DNNs) by only perturbing a few pixels (regularized by l_0 norm). Recent efforts combine it with another l_infty imperceptible on the perturbation magnitudes. The resultant sparse and…

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…

Robustness to adversarial attacks is typically evaluated with adversarial accuracy. While essential, this metric does not capture all aspects of robustness and in particular leaves out the question of how many perturbations can be found for…

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…