Related papers: ECLIPSE: Expunging Clean-label Indiscriminate Pois…

While implicit feedback is foundational to modern recommender systems, factors such as human error, uncertainty, and ambiguity in user behavior inevitably introduce significant noise into this feedback, adversely affecting the accuracy and…

Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have successfully achieved…

With the increasing prevalence of cloud computing platforms, ensuring data privacy during the cloud-based image related services such as classification has become crucial. In this study, we propose a novel privacypreserving image…

With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…

Learning from noisy labels is a critical challenge in machine learning, with vast implications for numerous real-world scenarios. While supervised contrastive learning has recently emerged as a powerful tool for navigating label noise, many…

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific…

For classification tasks, deep neural networks are prone to overfitting in the presence of label noise. Although existing methods are able to alleviate this problem at low noise levels, they encounter significant performance reduction at…

Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the…

Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright…

Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison…

Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms. Previous efforts tend to mitigate this problem via…

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

This paper presents Poisoning MorphNet, the first backdoor attack method on point clouds. Conventional adversarial attack takes place in the inference stage, often fooling a model by perturbing samples. In contrast, backdoor attack aims to…

Manually annotating datasets for training deep models is very labor-intensive and time-consuming. To overcome such inferiority, directly leveraging web images to conduct training data becomes a natural choice. Nevertheless, the presence of…

Privacy preserving has become increasingly critical with the emergence of social media. Unlearnable examples have been proposed to avoid leaking personal information on the Internet by degrading generalization abilities of deep learning…

Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require access to victim models which may significantly reduce their…

Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them…

The application of Deep Neural Networks (DNNs) to image denoising has notably challenged traditional denoising methods, particularly within complex noise scenarios prevalent in medical imaging. Despite the effectiveness of traditional and…

Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supervised learning (SSL). However, this approach has a…

Although noisy-label learning is often approached with discriminative methods for simplicity and speed, generative modeling offers a principled alternative by capturing the joint mechanism that produces features, clean labels, and corrupted…