Related papers: Backdoor Attacks Against Deep Image Compression vi…

Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing a large DNN model in edge computing scenarios (e.g., edge…

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already…

Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison…

Self-supervised learning (SSL) is pervasively exploited in training high-quality upstream encoders with a large amount of unlabeled data. However, it is found to be susceptible to backdoor attacks merely via polluting a small portion of…

Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into a smaller synthetic dataset. A model trained on this smaller…

The rapid expansion of connected devices has made them prime targets for cyberattacks. To address these threats, deep learning-based, data-driven intrusion detection systems (IDS) have emerged as powerful tools for detecting and mitigating…

Dense retrieval systems have been widely used in various NLP applications. However, their vulnerabilities to potential attacks have been underexplored. This paper investigates a novel attack scenario where the attackers aim to mislead the…

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of…

Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will perform abnormal actions leading to failures or malicious…

Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…

Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets, enabling broad generalization for graph machine learning. Despite that GFMs have attracted considerable attention recently, their…

Deep reinforcement learning (DRL) has made significant achievements in many real-world applications. But these real-world applications typically can only provide partial observations for making decisions due to occlusions and noisy sensors.…

Deep neural networks have been widely used in many critical applications, such as autonomous vehicles and medical diagnosis. However, their security is threatened by backdoor attacks, which are achieved by adding artificial patterns to…

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor…

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…

3D object detection plays an important role in autonomous driving; however, its vulnerability to backdoor attacks has become evident. By injecting ''triggers'' to poison the training dataset, backdoor attacks manipulate the detector's…

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the…

Deep learning models are vulnerable to backdoor attacks, where adversaries inject malicious functionality during training that activates on trigger inputs at inference time. Extensive research has focused on developing stealthy backdoor…

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…