Related papers: DeBackdoor: A Deductive Framework for Detecting Ba…

Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…

In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Such systems, while achieving the state-of-the-art performance on clean data, perform abnormally on inputs with…

Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attack surfaces. In particular, backdoor attacks allow attackers…

We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt…

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 attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This susceptibility primarily stems from the fact that these attacks…

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

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 neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

There have been several efforts in backdoor attacks, but these have primarily focused on the closed-set performance of classifiers (i.e., classification). This has left a gap in addressing the threat to classifiers' open-set performance,…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of…

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

The increasing importance of both deep neural networks (DNNs) and cloud services for training them means that bad actors have more incentive and opportunity to insert backdoors to alter the behavior of trained models. In this paper, we…

Recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks during the training process. Specifically, the adversaries intend to embed hidden backdoors in DNNs so that malicious model predictions can…

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…

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we…

Reusing off-the-shelf code snippets from online repositories is a common practice, which significantly enhances the productivity of software developers. To find desired code snippets, developers resort to code search engines through natural…

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…