相关论文: Defending Against Patch-based Backdoor Attacks on …

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of…

Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. (2023) marks the…

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to build downstream…

In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifiers. For instance, adversaries could inject malicious…

Backdoor defenses have been studied to alleviate the threat of deep neural networks (DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt some external training data from an untrusted third party, a robust…

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party…

Federated learning (FL) is a machine learning (ML) approach that allows the use of distributed data without compromising personal privacy. However, the heterogeneous distribution of data among clients in FL can make it difficult for the…

With the increasing usage of open-source software (OSS) components, vulnerabilities embedded within them are propagated to a huge number of underlying applications. In practice, the timely application of security patches in downstream…

Wild images on the web are vulnerable to backdoor (also called trojan) poisoning, causing machine learning models learned on these images to be injected with backdoors. Most previous attacks assumed that the wild images are labeled. In…

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…

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…

Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean…

Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one…

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily…

Recently, a special type of data poisoning (DP) attack targeting Deep Neural Network (DNN) classifiers, known as a backdoor, was proposed. These attacks do not seek to degrade classification accuracy, but rather to have the classifier learn…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks. First, we propose to quantitatively measure the trade-off between model accuracy and privacy losses…

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…

Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i.e., sever and clients only hold partial sub-networks and exchange…