With the increasing number of edited videos, many robust video fingerprinting schemes have been proposed to solve the problem of video content authentication. However, most of them either deal with the temporal and sp...
详细信息
In light of the escalating privacy risks in the big data era, this paper introduces an innovative model for the anonymization of big data streams, leveraging in-memory processing within the Spark framework. The approa...
详细信息
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lac...
详细信息
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lack formality. In this paper, we propose how to improve NMT formality with large language models (LLMs), which combines the style transfer and evaluation capabilities of an LLM and the high-quality translation generation ability of NMT models to improve NMT formality. The proposed method (namely INMTF) encompasses two approaches. The first involves a revision approach using an LLM to revise the NMT-generated translation, ensuring a formal translation style. The second approach employs an LLM as a reward model for scoring translation formality, and then uses reinforcement learning algorithms to fine-tune the NMT model to maximize the reward score, thereby enhancing the formality of the generated translations. Considering the substantial parameter size of LLMs, we also explore methods to reduce the computational cost of INMTF. Experimental results demonstrate that INMTF significantly outperforms baselines in terms of translation formality and translation quality, with an improvement of +9.19 style accuracy points in the German-to-English task and +2.16 COMET score in the Russian-to-English task. Furthermore, our work demonstrates the potential of integrating LLMs within NMT frameworks to bridge the gap between NMT outputs and the formality required in various real-world translation scenarios.
Federated recommender systems(FedRecs) have garnered increasing attention recently, thanks to their privacypreserving benefits. However, the decentralized and open characteristics of current FedRecs present at least t...
详细信息
Federated recommender systems(FedRecs) have garnered increasing attention recently, thanks to their privacypreserving benefits. However, the decentralized and open characteristics of current FedRecs present at least two ***, the performance of FedRecs is compromised due to highly sparse on-device data for each client. Second, the system's robustness is undermined by the vulnerability to model poisoning attacks launched by malicious users. In this paper, we introduce a novel contrastive learning framework designed to fully leverage the client's sparse data through embedding augmentation, referred to as CL4FedRec. Unlike previous contrastive learning approaches in FedRecs that necessitate clients to share their private parameters, our CL4FedRec aligns with the basic FedRec learning protocol, ensuring compatibility with most existing FedRec implementations. We then evaluate the robustness of FedRecs equipped with CL4FedRec by subjecting it to several state-of-the-art model poisoning attacks. Surprisingly, our observations reveal that contrastive learning tends to exacerbate the vulnerability of FedRecs to these attacks. This is attributed to the enhanced embedding uniformity, making the polluted target item embedding easily proximate to popular items. Based on this insight, we propose an enhanced and robust version of CL4FedRec(rCL4FedRec) by introducing a regularizer to maintain the distance among item embeddings with different popularity levels. Extensive experiments conducted on four commonly used recommendation datasets demonstrate that rCL4FedRec significantly enhances both the model's performance and the robustness of FedRecs.
By replacing the exponential decay function in the circular Airy beam (CAB) with a super-Gaussian function, we propose a novel abruptly autofocusing beam, the circular super-Gaussian Airy beam (CSGAB). Similar to CAB,...
详细信息
Photo sensing capability of an artificial synaptic device make it more valuable for brain-inspired computing systems, which can conquer the von Neumann bottleneck. In this letter, Ba0.7 Sr0.3 TiO3 (BST) based single l...
详细信息
Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) have been actively employed for tasks that are challenging for humans, such as scenarios like battlefield and disaster. Swarm unmanned systems, compr...
详细信息
Artificial Intelligence, including machine learning and deep convolutional neural networks (DCNNs), relies on complex algorithms and neural networks to process and analyze data. DCNNs for visual recognition often requ...
详细信息
Integrating Large Language Models (LLMs) with Knowledge Graphs (KGs) enhances the interpretability and performance of AI systems. This research comprehensively analyzes this integration, classifying approaches into th...
详细信息
Space/air communications have been envisioned as an essential part of the next-generation mobile communication networks for providing highquality global connectivity. However, the inherent broadcasting nature of wirel...
详细信息
Space/air communications have been envisioned as an essential part of the next-generation mobile communication networks for providing highquality global connectivity. However, the inherent broadcasting nature of wireless propagation environment and the broad coverage pose severe threats to the protection of private data. Emerging covert communications provides a promising solution to achieve robust communication security. Aiming at facilitating the practical implementation of covert communications in space/air networks, we present a tutorial overview of its potentials, scenarios, and key technologies. Specifically, first, the commonly used covertness constraint model, covert performance metrics, and potential application scenarios are briefly introduced. Then, several efficient methods that introduce uncertainty into the covert system are thoroughly summarized, followed by several critical enabling technologies, including joint resource allocation and deployment/trajectory design, multi-antenna and beamforming techniques, reconfigurable intelligent surface(RIS), and artificial intelligence algorithms. Finally, we highlight some open issues for future investigation.
暂无评论