相关论文: Adversarial Data Programming: Using GANs to Relax …

The proliferation of big data has brought an urgent demand for privacy-preserving data publishing. Traditional solutions to this demand have limitations on effectively balancing the tradeoff between privacy and utility of the released data.…

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…

Training an ensemble of diverse sub-models has been empirically demonstrated as an effective strategy for improving the adversarial robustness of deep neural networks. However, current ensemble training methods for image recognition…

Adversarial examples are delicately perturbed inputs, which aim to mislead machine learning models towards incorrect outputs. While most of the existing work focuses on generating adversarial perturbations in multi-class classification…

We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the…

We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive…

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…

While machine learning approaches to visual recognition offer great promise, most of the existing methods rely heavily on the availability of large quantities of labeled training data. However, in the vast majority of real-world settings,…

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that…

Generative Adversarial Networks (GAN) have shown great promise in tasks like synthetic image generation, image inpainting, style transfer, and anomaly detection. However, generating discrete data is a challenge. This work presents an…

Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also only having access…

We consider the task of training classifiers without labels. We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well against an adversary that chooses labels for training data. The weak…

Generative Adversarial Networks have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such…

Neural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. While previous works have shown that…

Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency,…

As the Internet grows in popularity, more and more classification jobs, such as IoT, finance industry and healthcare field, rely on mobile edge computing to advance machine learning. In the medical industry, however, good diagnostic…

To ensure that the data collected from human subjects is entrusted with a secret, rival labels are introduced to conceal the information provided by the participants on purpose. The corresponding learning task can be formulated as a noisy…

Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge…

Although neural networks could achieve state-of-the-art performance while recongnizing images, they often suffer a tremendous defeat from adversarial examples--inputs generated by utilizing imperceptible but intentional perturbation to…