相关论文: Shortcuts Everywhere and Nowhere: Exploring Multi-…

Deep learning models have been deployed in numerous real-world applications such as autonomous driving and surveillance. However, these models are vulnerable in adversarial environments. Backdoor attack is emerging as a severe security…

As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor attack and defense algorithms are being developed…

Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack…

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs that contain the adversary trigger. The major challenge for…

In recent years, machine learning models have been shown to be vulnerable to backdoor attacks. Under such attacks, an adversary embeds a stealthy backdoor into the trained model such that the compromised models will behave normally on clean…

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target…

Link prediction, inferring the undiscovered or potential links of the graph, is widely applied in the real-world. By facilitating labeled links of the graph as the training data, numerous deep learning based link prediction methods have…

Backdoor attacks have emerged as a critical security threat against deep neural networks in recent years. The majority of existing backdoor attacks focus on targeted backdoor attacks, where trigger is strongly associated to specific…

Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor trigger into the model at training time. While backdoor…

\textbf{G}raph \textbf{N}eural \textbf{N}etworks~(GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffic management. Recent researches highlight their…

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed…

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

Together with impressive advances touching every aspect of our society, AI technology based on Deep Neural Networks (DNN) is bringing increasing security concerns. While attacks operating at test time have monopolised the initial attention…

Deep neural networks have achieved impressive performance in various areas, but they are shown to be vulnerable to adversarial attacks. Previous works on adversarial attacks mainly focused on the single-task setting. However, in real…

Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing backdoor attacks require either retraining the classifier with…

While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the network's architecture. This involves injecting common…

With the widespread application of deep learning across various domains, concerns about its security have grown significantly. Among these, backdoor attacks pose a serious security threat to deep neural networks (DNNs). In recent years,…

As a critical threat to deep neural networks (DNNs), backdoor attacks can be categorized into two types, i.e., source-agnostic backdoor attacks (SABAs) and source-specific backdoor attacks (SSBAs). Compared to traditional SABAs, SSBAs are…