In recent years, intellectual property (IP), which represents literary, inventions, artistic works, etc, gradually attract more and more peoples attention. Particularly, with the rise of e-commerce, the IP not only represents the product design and b
rands, but also represents the images/videos displayed on e-commerce platforms. Unfortunately, some attackers adopt some adversarial methods to fool the well-trained logo detection model for infringement. To overcome this problem, a novel logo detector based on the mechanism of looking and thinking twice is proposed in this paper for robust logo detection. The proposed detector is different from other mainstream detectors, which can effectively detect small objects, long-tail objects, and is robust to adversarial images. In detail, we extend detectoRS algorithm to a cascade schema with an equalization loss function, multi-scale transformations, and adversarial data augmentation. A series of experimental results have shown that the proposed method can effectively improve the robustness of the detection model. Moreover, we have applied the proposed methods to competition ACM MM2021 Robust Logo Detection that is organized by Alibaba on the Tianchi platform and won top 2 in 36489 teams. Code is available at https://github.com/jiaxiaojunQAQ/Robust-Logo-Detection.
Recent advances in wireless communication and solid-state circuits together with the enormous demands of sensing ability have given rise to a new enabling technology, integrated sensing and communications (ISAC). The ISAC captures two main advantages
over dedicated sensing and communication functionalities: 1) Integration gain to efficiently utilize congested resources, and even, 2) Coordination gain to balance dual-functional performance or/and perform mutual assistance. Meanwhile, triggered by ISAC, we are also witnessing a paradigm shift in the ubiquitous IoT architecture, in which the sensing and communication layers are tending to converge into a new layer, namely, the signaling layer. In this paper, we first attempt to introduce a definition of ISAC, analyze the various influencing forces, and present several novel use cases. Then, we complement the understanding of the signaling layer by presenting several key benefits in the IoT era. We classify existing dominant ISAC solutions based on the layers in which integration is applied. Finally, several challenges and opportunities are discussed. We hope that this overview article will serve as a primary starting point for new researchers and offer a birds-eye view of the existing ISAC-related advances from academia and industry, ranging from solid-state circuitry, signal processing, and wireless communication to mobile computing.
Recent research has demonstrated that adding some imperceptible perturbations to original images can fool deep learning models. However, the current adversarial perturbations are usually shown in the form of noises, and thus have no practical meaning
. Image watermark is a technique widely used for copyright protection. We can regard image watermark as a king of meaningful noises and adding it to the original image will not affect peoples understanding of the image content, and will not arouse peoples suspicion. Therefore, it will be interesting to generate adversarial examples using watermarks. In this paper, we propose a novel watermark perturbation for adversarial examples (Adv-watermark) which combines image watermarking techniques and adversarial example algorithms. Adding a meaningful watermark to the clean images can attack the DNN models. Specifically, we propose a novel optimization algorithm, which is called Basin Hopping Evolution (BHE), to generate adversarial watermarks in the black-box attack mode. Thanks to the BHE, Adv-watermark only requires a few queries from the threat models to finish the attacks. A series of experiments conducted on ImageNet and CASIA-WebFace datasets show that the proposed method can efficiently generate adversarial examples, and outperforms the state-of-the-art attack methods. Moreover, Adv-watermark is more robust against image transformation defense methods.
Video classification is a challenging task in computer vision. Although Deep Neural Networks (DNNs) have achieved excellent performance in video classification, recent research shows adding imperceptible perturbations to clean videos can make the wel
l-trained models output wrong labels with high confidence. In this paper, we propose an effective defense framework to characterize and defend adversarial videos. The proposed method contains two phases: (1) adversarial video detection using temporal consistency between adjacent frames, and (2) adversarial perturbation reduction via denoisers in the spatial and temporal domains respectively. Specifically, because of the linear nature of DNNs, the imperceptible perturbations will enlarge with the increasing of DNNs depth, which leads to the inconsistency of DNNs output between adjacent frames. However, the benign video frames often have the same outputs with their neighbor frames owing to the slight changes. Based on this observation, we can distinguish between adversarial videos and benign videos. After that, we utilize different defense strategies against different attacks. We propose the temporal defense, which reconstructs the polluted frames with their temporally neighbor clean frames, to deal with the adversarial videos with sparse polluted frames. For the videos with dense polluted frames, we use an efficient adversarial denoiser to process each frame in the spatial domain, and thus purify the perturbations (we call it as spatial defense). A series of experiments conducted on the UCF-101 dataset demonstrate that the proposed method significantly improves the robustness of video classifiers against adversarial attacks.
The positivity of the partial transpose is in general only a necessary condition for separability. There exist quantum states that are not separable, but nevertheless are positive under partial transpose. States of this type are known as bound entang
led states meaning that these states are entangled but they do not allow distillation of pure entanglement by means of local operations and classical communication (LOCC). We present a parametrization of a class of $2times 2$ bound entangled Gaussian states for bipartite continuous-variable quantum systems with two modes on each side. We propose an experimental protocol for preparing a particular bound entangled state in quantum optics. We then discuss the robustness properties of this protocol with respect to the occupation number of thermal inputs and the degrees of squeezing.
Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an end-to-end imag
e compression model to defend adversarial examples: textbf{ComDefend}. The proposed model consists of a compression convolutional neural network (ComCNN) and a reconstruction convolutional neural network (ResCNN). The ComCNN is used to maintain the structure information of the original image and purify adversarial perturbations. And the ResCNN is used to reconstruct the original image with high quality. In other words, ComDefend can transform the adversarial image to its clean version, which is then fed to the trained classifier. Our method is a pre-processing module, and does not modify the classifiers structure during the whole process. Therefore, it can be combined with other model-specific defense models to jointly improve the classifiers robustness. A series of experiments conducted on MNIST, CIFAR10 and ImageNet show that the proposed method outperforms the state-of-the-art defense methods, and is consistently effective to protect classifiers against adversarial attacks.
In this paper, we obtain L{e}vys martingale characterization of $G$-Brownian motion without the nondegenerate condition. Base on this characterization, we prove the reflection principle of $G$-Brownian motion. Furthermore, we use Krylovs estimate to
get the reflection principle of $tilde{G}$-Brownian motion.
In this paper we study the stochastic differential equations driven by $G$-Brownian motion ($G$-SDEs for short). We extend the notion of conditional $G$-expectation from deterministic time to the more general optional time situation. Then, via this c
onditional expectation, we develop the strong Markov property for $G$-SDEs. In particular, we obtain the strong Markov property for $G$-Brownian motion. Some applications including the reflection principle for $G$-Brownian motion are also provided.
The Xinglong 2.16-m reflector is the first 2-meter class astronomical telescope in China. It was jointly designed and built by the Nanjing Astronomical Instruments Factory (NAIF), Beijing Astronomical Observatory (now National Astronomical Observator
ies, Chinese Academy of Sciences, NAOC) and Institute of Automation, Chinese Academy of Sciences in 1989. It is Ritchey-Chr{e}tien (R-C) reflector on an English equatorial mount and the effective aperture is 2.16 meters. It had been the largest optical telescope in China for $sim18$ years until the Guoshoujing Telescope (also called Large Sky Area Multi-Object Fiber Spectroscopic Telescope, LAMOST) and the Lijiang 2.4-m telescope were built. At present, there are three main instruments on the Cassegrain focus available: the Beijing Faint Object Spectrograph and Camera (BFOSC) for direct imaging and low resolution ($Rsim500-2000$) spectroscopy, the spectrograph made by Optomechanics Research Inc. (OMR) for low resolution spectroscopy (the spectral resolutions are similar to those of BFOSC) and the fiber-fed High Resolution Spectrograph (HRS, $Rsim30000-65000$). The telescope is widely open to astronomers all over China as well as international astronomical observers. Each year there are more than 40 ongoing observing projects, including 6-8 key projects. Recently, some new techniques and instruments (e.g., astro-frequency comb calibration system, polarimeter and adaptive optics) have been or will be tested on the telescope to extend its observing abilities.
In this paper, we consider the product space for two processes with independent increments under nonlinear expectations. By introducing a discretization method, we construct a nonlinear expectation under which the given two processes can be seen as a new process with independent increments.
