Related papers: FACTUAL: A Novel Framework for Contrastive Learnin…

As machine learning models grow in complexity and increasingly rely on publicly sourced data, such as the human-annotated labels used in training large language models, they become more vulnerable to label poisoning attacks. These attacks,…

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical…

Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that…

Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an…

Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the…

Recently, unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. Previous studies in unsupervised AT have mostly focused on implementing self-supervised…

It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks…

Recent studies have shown that deep learning-based hyperspectral image (HSI) classification models are highly vulnerable to adversarial attacks, posing significant security risks. Although most approaches attempt to enhance robustness by…

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Modern face recognition systems remain vulnerable to spoofing attempts, including both physical presentation attacks and digital forgeries. Traditionally, these two attack vectors have been handled by separate models, each targeting its own…

Training robust deep learning (DL) systems for disease detection from medical images is challenging due to limited images covering different disease types and severity. The problem is especially acute, where there is a severe class…

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

Autonomous vehicles are typical complex intelligent systems with artificial intelligence at their core. However, perception methods based on deep learning are extremely vulnerable to adversarial samples, resulting in security accidents. How…

Image forgery detection aims to detect and locate forged regions in an image. Most existing forgery detection algorithms formulate classification problems to classify pixels into forged or pristine. However, the definition of forged and…

Contrastive learning has achieved remarkable success on various high-level tasks, but there are fewer contrastive learning-based methods proposed for low-level tasks. It is challenging to adopt vanilla contrastive learning technologies…

Despite the remarkable progress of deep neural networks (DNNs) in various visual tasks, their vulnerability to adversarial examples raises significant security concerns. Recent adversarial training methods leverage inverse adversarial…

Contrastive learning (CL) has emerged as a powerful framework for learning representations of images and text in a self-supervised manner while enhancing model robustness against adversarial attacks. More recently, researchers have extended…

Existing studies show that node representations generated by graph neural networks (GNNs) are vulnerable to adversarial attacks, such as unnoticeable perturbations of adjacent matrix and node features. Thus, it is requisite to learn robust…

Adversarial training is one of the most effective approaches against adversarial attacks. However, adversarial training has primarily been studied in scenarios where data for all classes is provided, with limited research conducted in the…