相关论文: Memory Backdoor Attacks on Neural Networks

Federated learning (FL) is an emerging distributed machine learning paradigm proposed for privacy preservation. Unlike traditional centralized learning approaches, FL enables multiple users to collaboratively train a shared global model…

Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show…

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By…

Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications. While backdoor attacks have been…

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

Backdoor learning has become an emerging research area towards building a trustworthy machine learning system. While a lot of works have studied the hidden danger of backdoor attacks in image or text classification, there is a limited…

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…

With the rapid expansion of data lakes storing health data and hosting AI algorithms, a prominent concern arises: how safe is it to export machine learning models from these data lakes? In particular, deep network models, widely used for…

Data lakes enable the training of powerful machine learning models on sensitive, high-value medical datasets, but also introduce serious privacy risks due to potential leakage of protected health information. Recent studies show adversaries…

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…

Deep Neural Networks (DNNs) have shown great promise in various domains. However, vulnerabilities associated with DNN training, such as backdoor attacks, are a significant concern. These attacks involve the subtle insertion of triggers…

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…

To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data. This practice is widely regarded as secure,…

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…

As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject. Even those that deploy neural networks embedded in physical devices may wish to…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. By…

In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a…

Federated learning (FL) enables multiple clients to train a model without compromising sensitive data. The decentralized nature of FL makes it susceptible to adversarial attacks, especially backdoor insertion during training. Recently, the…