Related papers: Property Inference From Poisoning
Adversarial attacks alter NLP model predictions by perturbing test-time inputs. However, it is much less understood whether, and how, predictions can be manipulated with small, concealed changes to the training data. In this work, we…
Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em…
Poisoning attacks compromise the training phase of federated learning (FL) such that the learned global model misclassifies attacker-chosen inputs called target inputs. Existing defenses mainly focus on protecting the training phase of FL…
Poisoning attacks have emerged as a significant security threat to machine learning algorithms. It has been demonstrated that adversaries who make small changes to the training set, such as adding specially crafted data points, can hurt the…
Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model…
A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…
Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…
Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…
Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed.…
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…
Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…
This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the data in a malicious manner can drastically deteriorate the…
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…
Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…
Machine learning is data hungry; the more data a model has access to in training, the more likely it is to perform well at inference time. Distinct parties may want to combine their local data to gain the benefits of a model trained on a…
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…
Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…
Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been studied mostly for classification, even though regression…
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…
Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present…