Related papers: Gradient-Based Adversarial and Out-of-Distribution…

A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output…

Despite high accuracy of Convolutional Neural Networks (CNNs), they are vulnerable to adversarial and out-distribution examples. There are many proposed methods that tend to detect or make CNNs robust against these fooling examples.…

Graph learning has been crucial to many real-world tasks, but they are often studied with a closed-world assumption, with all possible labels of data known a priori. To enable effective graph learning in an open and noisy environment, it is…

An accurate and substantial dataset is essential for training a reliable and well-performing model. However, even manually annotated datasets contain label errors, not to mention automatically labeled ones. Previous methods for label…

There has been a remarkable progress in the accuracy of semantic segmentation due to the capabilities of deep learning. Unfortunately, these methods are not able to generalize much further than the distribution of their training data and…

Deep neural network, despite its remarkable capability of discriminating targeted in-distribution samples, shows poor performance on detecting anomalous out-of-distribution data. To address this defect, state-of-the-art solutions choose to…

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…

Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of…

We propose a metric -- Projection Norm -- to predict a model's performance on out-of-distribution (OOD) data without access to ground truth labels. Projection Norm first uses model predictions to pseudo-label test samples and then trains a…

Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these…

Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass defense mechanisms.…

Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However,…

Deep neural networks (DNNs) are vulnerable to adversarial examples, which may lead to catastrophe in security-critical domains. Numerous detection methods are proposed to characterize the feature uniqueness of adversarial examples, or to…

Out-of-distribution (OOD) detection lies at the heart of robust artificial intelligence (AI), aiming to identify samples from novel distributions beyond the training set. Recent approaches have exploited feature representations as…

We propose a detector of adversarial samples that is based on the view of neural networks as discrete dynamic systems. The detector tells clean inputs from abnormal ones by comparing the discrete vector fields they follow through the…

Due to the unsupervised nature of anomaly detection, the key to fueling deep models is finding supervisory signals. Different from current reconstruction-guided generative models and transformation-based contrastive models, we devise novel…

Anomaly detection is to recognize samples that differ in some respect from the training observations. These samples which do not conform to the distribution of normal data are called outliers or anomalies. In real-world anomaly detection…

Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or from OoD. Diffusion Models (DMs) are recently utilized in OoD…

Deep neural networks often suffer from overconfidence which can be partly remedied by improved out-of-distribution detection. For this purpose, we propose a novel approach that allows for the generation of out-of-distribution datasets based…

Recent work has proposed several efficient approaches for generating gradient-based adversarial perturbations on embeddings and proved that the model's performance and robustness can be improved when they are trained with these contaminated…