Related papers: PoisonedEncoder: Poisoning the Unlabeled Pre-train…
We investigate adversarial attacks for autoencoders. We propose a procedure that distorts the input image to mislead the autoencoder in reconstructing a completely different target image. We attack the internal latent representations,…
Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…
Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…
Self-supervised learning (SSL) is pervasively exploited in training high-quality upstream encoders with a large amount of unlabeled data. However, it is found to be susceptible to backdoor attacks merely via polluting a small portion of…
Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…
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…
Gathering enough images to train a deep computer vision model is a constant challenge. Unfortunately, collecting images from unknown sources can leave your model s behavior at risk of being manipulated by a dirty-label or clean-label attack…
Self-supervised pretraining on unlabeled data followed by supervised fine-tuning on labeled data is a popular paradigm for learning from limited labeled examples. We extend this paradigm to the classical positive unlabeled (PU) setting,…
To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data. This practice is widely regarded as secure,…
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…
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…
Dense retrieval has shown promising results in many information retrieval (IR) related tasks, whose foundation is high-quality text representation learning for effective search. Some recent studies have shown that autoencoder-based language…
Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…
Wild images on the web are vulnerable to backdoor (also called trojan) poisoning, causing machine learning models learned on these images to be injected with backdoors. Most previous attacks assumed that the wild images are labeled. In…
Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to…
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…
Deep learning has become a cornerstone of modern artificial intelligence, enabling transformative applications across a wide range of domains. As the core element of deep learning, the quality and security of training data critically…
The increasing level of sound pollution in marine environments poses an increased threat to ocean health, making it crucial to monitor underwater noise. By monitoring this noise, the sources responsible for this pollution can be mapped.…
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…
This paper proposes a novel, data-agnostic, model poisoning attack on Federated Learning (FL), by designing a new adversarial graph autoencoder (GAE)-based framework. The attack requires no knowledge of FL training data and achieves both…