相关论文: Radioactive data: tracing through training

Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Understanding when and how much a model gradient leaks information about the training sample is an important question in privacy. In this paper, we present a surprising result: even without training or memorizing the data, we can fully…

Deep models are highly susceptible to adversarial attacks. Such attacks are carefully crafted imperceptible noises that can fool the network and can cause severe consequences when deployed. To encounter them, the model requires training…

In a data-driven world, datasets constitute a significant economic value. Dataset owners who spend time and money to collect and curate the data are incentivized to ensure that their datasets are not used in ways that they did not…

A recent line of work has uncovered a new form of data poisoning: so-called \emph{backdoor} attacks. These attacks are particularly dangerous because they do not affect a network's behavior on typical, benign data. Rather, the network only…

Convolutional neural networks memorize part of their training data, which is why strategies such as data augmentation and drop-out are employed to mitigate overfitting. This paper considers the related question of "membership inference",…

The rise of deep learning (DL) has led to a surging demand for training data, which incentivizes the creators of DL models to trawl through the Internet for training materials. Meanwhile, users often have limited control over whether their…

For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential malware sample, suspicious email) is deemed…

Recently, a backdoor data poisoning attack was proposed, which adds mislabeled examples to the training set, with an embedded backdoor pattern, aiming to have the classifier learn to classify to a target class whenever the backdoor pattern…

Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…

Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural…

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

Identifying the training datasets that influence a language model's outputs is essential for minimizing the generation of harmful content and enhancing its performance. Ideally, we can measure the influence of each dataset by removing it…

Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…

The expanding usage of complex machine learning methods like deep learning has led to an explosion in human activity recognition, particularly applied to health. In particular, as part of a larger body sensor network system, face and…

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

The ability to accurately estimate risk of developing breast cancer would be invaluable for clinical decision-making. One promising new approach is to integrate image-based risk models based on deep neural networks. However, one must take…

Deep Neural Networks (DNNs) are widely used for traffic sign recognition because they can automatically extract high-level features from images. These DNNs are trained on large-scale datasets obtained from unknown sources. Therefore, it is…