相关论文: Nonlinear Transformations Against Unlearnable Data…

Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the…

Unlearnable examples (ULEs) aim to protect data from unauthorized usage for training DNNs. Existing work adds $\ell_\infty$-bounded perturbations to the original sample so that the trained model generalizes poorly. Such perturbations,…

Deep neural networks with their large number of parameters are highly flexible learning systems. The high flexibility in such networks brings with some serious problems such as overfitting, and regularization is used to address this…

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to…

Most existing approaches to train a unified multi-organ segmentation model from several single-organ datasets require simultaneously access multiple datasets during training. In the real scenarios, due to privacy and ethics concerns, the…

Recent advancements in AI models are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on…

Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…

Deep learning based methods have seen a massive rise in popularity for hyperspectral image classification over the past few years. However, the success of deep learning is attributed greatly to numerous labeled samples. It is still very…

The acquisition of labels for supervised learning can be expensive. To improve the sample efficiency of neural network regression, we study active learning methods that adaptively select batches of unlabeled data for labeling. We present a…

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands --…

Data is used widely by service providers as input to inference systems to perform decision making for authorized tasks. The raw data however allows a service provider to infer other sensitive information it has not been authorized for. We…

Several companies often safeguard their trained deep models (i.e., details of architecture, learnt weights, training details etc.) from third-party users by exposing them only as black boxes through APIs. Moreover, they may not even provide…

Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to…

When a deep learning model is deployed in the wild, it can encounter test data drawn from distributions different from the training data distribution and suffer drop in performance. For safe deployment, it is essential to estimate the…

Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

Despite extensive research spanning several decades, class imbalance is still considered a profound difficulty for both machine learning and deep learning models. While data oversampling is the foremost technique to address this issue,…

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been proposed in the recent…

Recent data-privacy laws have sparked interest in machine unlearning, which involves removing the effect of specific training samples from a learnt model as if they were never present in the original training dataset. The challenge of…