Related papers: Undetectable Backdoors in Model Parameters: Hiding…

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,…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…

Backdoor attacks pose serious security threats to deep neural networks (DNNs). Backdoored models make arbitrarily (targeted) incorrect predictions on inputs embedded with well-designed triggers while behaving normally on clean inputs. Many…

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored…

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…

Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a source class is embedded with the backdoor pattern (BP).…

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Recently, a backdoor data poisoning attack was proposed, which adds mislabeled examples to the training set, with an embedded backdoor pattern, aiming to have the classifier learn to classify to a target class whenever the backdoor pattern…

Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can manipulate the…

In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…

Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features may behave like triggers, causing misclassification once…

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that contain evident patterns, rendering remarkable attack effects…

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…