The demand for resilient watermarking technology in the context of the screen-shooting scenario is steadily on the rise. The principal objective of this technique is to embed messages into the cover image, with the ability to effectively recover the message from the screen-captured image at the extraction end. However, current watermarking methods result in low visual quality watermarked images and are insufficiently robust in screen-shooting scenarios. This is mainly because they only utilize spatial domain information during embedding, and they do not consider the impact of noise that introduced during screen capturing. This paper introduces an innovative network framework, including the wavelet domain concatenation and recovery mechanism, to overcome the dual challenges encountered in robust watermarking, namely visual fidelity and robustness. For fidelity, we present a cascade network operating in the wavelet domain. This network excel at detecting watermark information in the wavelet domain. This capability makes it more sensitive to high and low-frequency details. Discrete wavelet transform can make CNN focus on different frequency characteristics, and the use of discrete inverse wavelet transform in upsampling can make the information bluehigh fidelity. As a result, it can more accurately identify and preserve critical visual details in this frequency domain, leading to an overall enhancement in visual quality. For robustness, a recovery network is specifically designed to mitigate the influence of noise introduced during screen-shooting on watermark information extraction. Experimental validation of our proposed method substantiates its effectiveness in significantly enhancing the visual quality and the accuracy of the watermarked images.

Relying on weak cross-Kerr nonlinearities, we propose a nearly deterministic generation scheme of the three-photon polarization-entangled perfect $W$ state which can be applied to the perfect teleportation of an unknown single-photon state and has robust entanglement against the loss of one photon of them. Three photons entangle together by virtue of the bus function of the coherent state serving as the intermediate among them. In the scheme, three processes are executed successively and two kinds of modules are inserted into the circuit, where the homodyne measurement and the photon number measurement are aptly performed. By means of classical feedforward techniques, single-photon unitary transformation operations are performed on the corresponding photons based on the obtained measurement outcomes, by which the generation efficiency of the perfect $W$ state aims to nearly unity. Moreover, some currently available optical elements are applied in the generation process, which offer facilities for the practical implementation.

Text images, such as scanned documents, certificates, and chat-box screenshots, are commonly used for multimodal communication. However, the rise of advanced deep image editing tools raises concerns about the authenticity of text images. Unlike natural images, even subtle tampering in text images, like a single character, can substantially alter the semantics. To address this issue, we propose a robust network framework for detecting and localizing text image forgeries. This framework involves forgery traces enhancement and multiscale attention-based forgery localization. Specifically, we introduce a deep module to enhance forgery traces from multiple domains, reducing distraction from the image background and facilitating the forgery localization. An efficient encoder-decoder network is devised by fusing high-level semantics with low-level details using a multiscale attention module. Through joint restoration and multiscale forgery feature learning, even delicately tampered regions can be effectively exposed. To evaluate the framework under real-world distortion scenarios, we create a large-scale dataset featuring various tampering methods and distortions. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both accuracy and robustness, especially for the small tampering regions.

Although neural network-based speech recognition models have enjoyed significant success in many acoustic systems, they are susceptible to be attacked by the adversarial examples. In this work, we make first step towards using generative adversarial network (GAN) for constructing the targeted speech adversarial examples. Specifically, we integrate the target speech recognition network with GAN framework, which can then be formulated as a three-party game. The generator in GAN aims at generating perturbation that could make the target network misclassified to a specific target, while simultaneously fooling the discriminator treating the adversarial example as a beguine one. The discriminator is to distinguish the crafted examples from the geniue samples. The classification error of the target network is back-propagated via gradient flow to the generator for updating. The target network is responsible for back-propagating the classification error via gradients to the generator for updating, but the target network itself is freezed. With the carefully designed network architecture, loss function and training strategy, we successfully train a generator that could generate the adversarial perturbation for a given speech clip and a target label. Experiential results show that the generated adversarial examples could effectively fool the state-of-the-art speech classification networks, while attaining an acceptable auditory perception quality. In addition, our proposed method runs much faster than the prevalent optimization-based schemes. To facilitate reproducible research, codes, models and data are publicly available at https://github.com/winterwindwang/SpeechAdvGan.

With the assistance of weak cross-Kerr nonlinearities, we present a preparation scheme of four-photon polarization-entangled decoherence-free states, which can be used to construct the minimal optical decoherence-free subspaces where a logical qubit is fully protected against collective decoherence. To complete the preparation task, one spatial entanglement process, two polarization entanglement processes, and one detecting process are applied. The fulfillments of the above processes are contributed by a cross-Kerr nonlinear interaction between the signal photons and a coherent state via Kerr media. Exploiting the available single-photon resource and simple linear optics elements, this scheme is feasible and desirable to be extended to the construction of multiphoton decoherence-free states against the collective decoherence.