Related papers: Trojan Cleansing with Neural Collapse

Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has shown that outsourced…

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…

We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during…

Federated learning (FL) systems allow decentralized data-owning clients to jointly train a global model through uploading their locally trained updates to a centralized server. The property of decentralization enables adversaries to craft…

Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored. This work investigates backdoor attacks, which implant hidden triggers that cause malicious…

While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplored. In this paper, we shed light on how model leaderboards…

Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…

The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications. Recently, the deployed DNNs have been demonstrated to be vulnerable to Trojan attacks, which manipulate…

Deep neural networks are susceptible to \emph{adversarial} attacks. In computer vision, well-crafted perturbations to images can cause neural networks to make mistakes such as confusing a cat with a computer. Previous adversarial attacks…

Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…

Graph neural networks (GNNs) are widely used for learning from graph-structured data in domains such as social networks, recommender systems, and financial platforms. To comply with privacy regulations like the GDPR, CCPA, and PIPEDA,…

Backdoor attack against deep neural networks is currently being profoundly investigated due to its severe security consequences. Current state-of-the-art backdoor attacks require the adversary to modify the input, usually by adding a…

Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical…

As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…

Backdoor attacks embed malicious behaviors into Large Language Models (LLMs), enabling adversaries to trigger harmful outputs or bypass safety controls. However, the persistence of the implanted backdoors under user-driven post-deployment…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Machine learning models in the wild have been shown to be vulnerable to Trojan attacks during training. Although many detection mechanisms have been proposed, strong adaptive attackers have been shown to be effective against them. In this…

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks…

With the rapid growth of the number of devices on the Internet, malware poses a threat not only to the affected devices but also their ability to use said devices to launch attacks on the Internet ecosystem. Rapid malware classification is…

Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign inputs, yet invokes a predefined malicious behavior when its…