相关论文: CLIP-Guided Generative Networks for Transferable T…

Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown…

In this paper, we address the task of semantic-guided scene generation. One open challenge in scene generation is the difficulty of the generation of small objects and detailed local texture, which has been widely observed in global…

We show that we can easily design a single adversarial perturbation $P$ that changes the class of $n$ images $X_1,X_2,\dots,X_n$ from their original, unperturbed classes $c_1, c_2,\dots,c_n$ to desired (not necessarily all the same) classes…

In recent years, patch representation learning has emerged as a necessary research direction for exploiting the capabilities of machine learning in software generation. These representations have driven significant performance enhancements…

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

Surrogate-based black-box attacks have exposed the heightened vulnerability of DNNs. These attacks are designed to craft adversarial examples for any samples with black-box target feedback for only a given set of samples. State-of-the-art…

Transferable adversarial attacks pose significant threats to deep neural networks, particularly in black-box scenarios where internal model information is inaccessible. Studying adversarial attack methods helps advance the performance of…

Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack…

In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial attacks and…

Conditional generative adversarial networks (cGANs) have demonstrated remarkable success due to their class-wise controllability and superior quality for complex generation tasks. Typical cGANs solve the joint distribution matching problem…

Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations of these systems. For robot…

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

As a widely deployed security scheme, text-based CAPTCHAs have become more and more difficult to resist machine learning-based attacks. So far, many researchers have conducted attacking research on text-based CAPTCHAs deployed by different…

We explore recurrent encoder multi-decoder neural network architectures for semi-supervised sequence classification and reconstruction. We find that the use of multiple reconstruction modules helps models generalize in a classification task…

Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning. However, the requirement of isolated single modal demonstrations…

Deep neural networks (DNNs) have been demonstrated to be vulnerable to well-crafted \emph{adversarial examples}, which are generated through either well-conceived $\mathcal{L}_p$-norm restricted or unrestricted attacks. Nevertheless, the…

Controlling the model to generate texts of different categories is a challenging task that is receiving increasing attention. Recently, generative adversarial networks (GANs) have shown promising results for category text generation.…

Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification performance on natural examples), we investigate and identify…

Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode…

We propose a novel GAN training scheme that can handle any level of labeling in a unified manner. Our scheme introduces a form of artificial labeling that can incorporate manually defined labels, when available, and induce an alignment…