相关论文: Silent Killer: A Stealthy, Clean-Label, Black-Box …

Recently, DL has been exploited in wireless communications such as modulation classification. However, due to the openness of wireless channel and unexplainability of DL, it is also vulnerable to adversarial attacks. In this correspondence,…

With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in…

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

Due to the increasing computational demand of Deep Neural Networks (DNNs), companies and organizations have begun to outsource the training process. However, the externally trained DNNs can potentially be backdoor attacked. It is crucial to…

At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by victims using the…

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

The backdoor attack poses a new security threat to deep neural networks. Existing backdoor often relies on visible universal trigger to make the backdoored model malfunction, which are not only usually visually suspicious to human but also…

Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and…

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific…

Data poisoning -- the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data -- is an emerging threat in the context of neural networks. Existing attacks for data poisoning…

The vulnerabilities to backdoor attacks have recently threatened the trustworthiness of machine learning models in practical applications. Conventional wisdom suggests that not everyone can be an attacker since the process of designing the…

Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows attackers to control the model to misclassify poisoned…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently,…

Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Neural networks have demonstrated remarkable success in learning and solving complex tasks in a variety of fields. Nevertheless, the rise of those networks in modern computing has been accompanied by concerns regarding their vulnerability…

Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor…

Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by…

Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs.…