Related papers: Robust Training Using Natural Transformation
Adversarial training is a popular defense strategy against attack threat models with bounded Lp norms. However, it often degrades the model performance on normal images and the defense does not generalize well to novel attacks. Given the…
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…
We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained…
With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…
We propose to improve unconditional Generative Adversarial Networks (GAN) by training the self-supervised learning with the adversarial process. In particular, we apply self-supervised learning via the geometric transformation on input…
The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input…
Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the…
Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense.…
Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data,…
Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…
In recent years, there has been growing concern over the vulnerability of convolutional neural networks (CNNs) to image perturbations. However, achieving general robustness against different types of perturbations remains challenging, in…
Latent diffusion models have recently demonstrated superior capabilities in many downstream image synthesis tasks. However, customization of latent diffusion models using unauthorized data can severely compromise the privacy and…
Recent studies have shown that deep convolutional neural networks (DCNN) are vulnerable to adversarial examples and sensitive to perceptual quality as well as the acquisition condition of images. These findings raise a big concern for the…
Deep networks for computer vision are not reliable when they encounter adversarial examples. In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference. By introducing…
This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes…
Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…
Deep neural networks have demonstrated high accuracy in image classification tasks. However, they were shown to be weak against adversarial examples: a small perturbation in the image which changes the classification output dramatically. In…
Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning systems, and thus improving robustness to distribution shifts is essential for practical applications. To improve robustness, we study an image…
Deep learning models can be fooled by small $l_p$-norm adversarial perturbations and natural perturbations in terms of attributes. Although the robustness against each perturbation has been explored, it remains a challenge to address the…
Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…