相关论文: Temporal Robustness against Data Poisoning

Recommender systems have become an integral part of online services to help users locate specific information in a sea of data. However, existing studies show that some recommender systems are vulnerable to poisoning attacks, particularly…

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…

Targeted data poisoning (TDP) aims to compromise the model's prediction on a specific (test) target by perturbing a small subset of training data. Existing work on TDP has focused on an overly ideal threat model in which the same image…

Poisoning attacks, in which an attacker adversarially manipulates the training dataset of a machine learning (ML) model, pose a significant threat to ML security. Beta Poisoning is a recently proposed poisoning attack that disrupts model…

Data poisoning has been proposed as a compelling defense against facial recognition models trained on Web-scraped pictures. Users can perturb images they post online, so that models will misclassify future (unperturbed) pictures. We…

Instance-targeted data poisoning attacks, where an adversary corrupts a training set to induce errors on specific test points, have raised significant concerns. Balcan et al (2022) proposed an approach to addressing this challenge by…

We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide performance guarantees for the trained model on the original data (not including the poison records) by training…

The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called {\em workers}).…

The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and varied inference methods. While prior research on data…

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.…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Both fair machine learning and adversarial learning have been extensively studied. However, attacking fair machine learning models has received less attention. In this paper, we present a framework that seeks to effectively generate…

Imperceptible poisoning attacks on entire datasets have recently been touted as methods for protecting data privacy. However, among a number of defenses preventing the practical use of these techniques, early-stopping stands out as a…

Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning…

Recommender systems have been shown to be vulnerable to poisoning attacks, where malicious data is injected into the dataset to cause the recommender system to provide biased recommendations. To defend against such attacks, various robust…

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…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

Regression models, which are widely used from engineering applications to financial forecasting, are vulnerable to targeted malicious attacks such as training data poisoning, through which adversaries can manipulate their predictions.…

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…