相关论文: Fooling Partial Dependence via Data Poisoning

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…

We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal…

Model poisoning attacks on federated learning (FL) intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired…

Data poisoning -- the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data -- is an emerging threat in the context of neural networks. Existing attacks for data poisoning…

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…

Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only against a specific type of targeted attack, significantly degrade…

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…

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…

Machine learning based data-driven technologies have shown impressive performances in a variety of application domains. Most enterprises use data from multiple sources to provide quality applications. The reliability of the external data…

The distributed nature of local differential privacy (LDP) invites data poisoning attacks and poses unforeseen threats to the underlying LDP-supported applications. In this paper, we propose a comprehensive mitigation framework for popular…

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Federated learning (FL) combined with local differential privacy (LDP) enables privacy-preserving model training across decentralized data sources. However, the decentralized data-management paradigm leaves LDPFL vulnerable to participants…

Fair machine learning seeks to mitigate model prediction bias against certain demographic subgroups such as elder and female. Recently, fair representation learning (FRL) trained by deep neural networks has demonstrated superior…

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

In recent years, there has been a growing interest in the effects of data poisoning attacks on data-driven control methods. Poisoning attacks are well-known to the Machine Learning community, which, however, make use of assumptions, such as…

We study data poisoning attacks in learning from human preferences. More specifically, we consider the problem of teaching/enforcing a target policy $\pi^\dagger$ by synthesizing preference data. We seek to understand the susceptibility of…

As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction.…

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in the industry, their outputs could affect business decision making,…

Federated learning (FL) is a feasible technique to learn personalized recommendation models from decentralized user data. Unfortunately, federated recommender systems are vulnerable to poisoning attacks by malicious clients. Existing…