Related papers: Data Taggants: Dataset Ownership Verification via …

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…

Backdoor data poisoning is a crucial technique for ownership protection and defending against malicious attacks. Embedding hidden triggers in training data can manipulate model outputs, enabling provenance verification, and deterring…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

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),…

Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to…

Backdoor-based watermarking schemes were proposed to protect the intellectual property of artificial intelligence models, especially deep neural networks, under the black-box setting. Compared with ordinary backdoors, backdoor-based…

Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware specified label. For backdoor attacks to bypass human…

With the increase in machine learning (ML) applications in different domains, incentives for deceiving these models have reached more than ever. As data is the core backbone of ML algorithms, attackers shifted their interest toward…

Deep neural networks (DNNs) rely heavily on high-quality open-source datasets (e.g., ImageNet) for their success, making dataset ownership verification (DOV) crucial for protecting public dataset copyrights. In this paper, we find existing…

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also…

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…

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…

Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded by privacy and ethical concerns associated with sensitive…

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high clean accuracy in…

Watermarking has become a plausible candidate for ownership verification and intellectual property protection of deep neural networks. Regarding image classification neural networks, current watermarking schemes uniformly resort to backdoor…

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the…

As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques that can be used to confirm the ownership of a particular…