相关论文: CUBA: Controlled Untargeted Backdoor Attack agains…

Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of…

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been…

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…

In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models. However, many existing approaches require substantial…

Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and create a more stealthy backdoor attack method, a…

Heterogeneous graph neural networks (HGNNs) have achieved strong performance in many real-world applications, yet targeted backdoor poisoning on heterogeneous graphs remains less studied. We consider backdoor attacks for heterogeneous node…

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors…

By injecting a small number of poisoned samples into the training set, backdoor attacks aim to make the victim model produce designed outputs on any input injected with pre-designed backdoors. In order to achieve a high attack success rate…

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses…

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model…

Backdoor attack is a new AI security risk that has emerged in recent years. Drawing on the previous research of adversarial attack, we argue that the backdoor attack has the potential to tap into the model learning process and improve model…

Federated learning enables multiple clients to collaboratively contribute to the learning of a global model orchestrated by a central server. This learning scheme promotes clients' data privacy and requires reduced communication overheads.…

Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples. The attacked model behaves normally on benign…

Heterogeneous graph neural networks (HGNNs) have recently drawn increasing attention for modeling complex multi-relational data in domains such as recommendation, finance, and social networks. While existing research has been largely…

Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable to backdoor attacks, where some specific trigger patterns…

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled…