Related papers: HINT: Healthy Influential-Noise based Training to …
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…
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…
State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…
Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning…
Protecting the use of audio datasets is a major concern for data owners, particularly with the recent rise of audio deep learning models. While watermarks can be used to protect the data itself, they do not allow to identify a deep learning…
Data Poisoning (DP) is an effective attack that causes trained classifiers to misclassify their inputs. DP attacks significantly degrade a classifier's accuracy by covertly injecting attack samples into the training set. Broadly applicable…
As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of…
Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by…
The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…
Graph-based Semi-Supervised Learning (GSSL) is a practical solution to learn from a limited amount of labelled data together with a vast amount of unlabelled data. However, due to their reliance on the known labels to infer the unknown…
Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…
Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed to counteract these attacks, they often come at the cost of…
Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…
Adversarial training is widely believed to be a reliable approach to improve model robustness against adversarial attack. However, in this paper, we show that when trained on one type of poisoned data, adversarial training can also be…
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…
Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data sanitization: first filter…
Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification of an unmodified test image and as such breach model…
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…
Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…
Targeted training-set attacks inject malicious instances into the training set to cause a trained model to mislabel one or more specific test instances. This work proposes the task of target identification, which determines whether a…