Journal of Information and Intelligence最新文献

Sensors are widely applied in the collection of voice data. Since many attributes of voice data are sensitive such as user emotions, identity, raw voice collection may lead serious privacy threat. In the past, traditional feature extraction obtains and encrypts voice features that are then transmitted to upstream servers. In order to avoid sensitive attribute disclosure, it is necessary to separate the sensitive attributes from non-sensitive attributes of voice data. Motivated by this, user-optional privacy transmission framework for voice data (called: Voice Fence Wall) is proposed. Firstly, we provide user-optional, which means users can choose the attributes (sensitive attributes) they want to be protected. Secondly, Voice Fence Wall utilizes minimum mutual information (MI) to reduce the correlation between sensitive and non-sensitive attributes, thereby separating these attributes. Finally, only the separated non-sensitive attributes are transmitted to the upstream server, the quality of voice services is satisfied without leaking sensitive attributes. To verify the reliability and practicability, three voice datasets are used to evaluate the model, the experiments demonstrate that Voice Fence Wall not only effectively separates attributes to resist attribute inference attacks, but also outperforms related work in terms of classification performance. Specifically, our framework achieves 89.84 ​% accuracy in sentiment recognition and 6.01 ​% equal error rate in voice authentication.

Detecting ink mismatch is a significant challenge in verifying the authenticity of documents, especially when dealing with uneven ink distribution. Conventional imaging methods frequently fail to distinguish visually similar inks. Our study presents a novel hyperspectral unmixing approach to detect ink mismatches in unbalanced clusters. The proposed method identifies unique spectral characteristics of different inks employing k-means clustering and Gaussian mixture models (GMMs) to perform color segmentation on different ink types and utilizes elbow estimation and silhouette coefficient to evaluate the number of inks estimation precisely. For a more accurate estimation of quantity, which is generally not an attribute of clustering methods, we employed entropy calculations in the red, green, and blue depth channels for precise abundance estimation of ink. This unique combination of basic techniques in conjunction exhibits better efficacy in performing ink unmixing and provides a real-world document forensic solution compared to current methods that rely on assumptions like prior knowledge of the inks used in a document and deep learning-based methods that rely heavily on abundant training datasets. We evaluate our approach on the iVision handwritten hyperspectral images dataset (iVision HHID), which is a comprehensive and rich dataset that surpasses the commonly-used UWA writing inks hyperspectral images (WIHSI) database in size and diversity. This study has accomplished the unmixing task with three main challenges: unmixing of diverse ink spectral signatures (149 spectral bands instead of 33 bands in the previous dataset), without using prior knowledge and assumptions about the number of inks used in the questioned document, and not requiring large training data for performing unmixing. Furthermore, the security of the proposed document authentication methodology to address the likelihood of forgeries or manipulations in questioned documents is enhanced as compared to previous works relying on known inks and known spectrum. Randomization techniques and anomaly detection mechanisms are used in our methodology which increases the difficulty for adversaries to predict and manipulate specific aspects of the input data in questioned documents, thereby enhancing the robustness of our method. The code for conducting this research can be accessed at GitHub repository.

AutoML (Automated Machine Learning) is an emerging field that aims to automate the process of building machine learning models. AutoML emerged to increase productivity and efficiency by automating as much as possible the inefficient work that occurs while repeating this process whenever machine learning is applied. In particular, research has been conducted for a long time on technologies that can effectively develop high-quality models by minimizing the intervention of model developers in the process from data preprocessing to algorithm selection and tuning. In this semantic review research, we summarize the data processing requirements for AutoML approaches and provide a detailed explanation. We place greater emphasis on neural architecture search (NAS) as it currently represents a highly popular sub-topic within the field of AutoML. NAS methods use machine learning algorithms to search through a large space of possible architectures and find the one that performs best on a given task. We provide a summary of the performance achieved by representative NAS algorithms on the CIFAR-10, CIFAR-100, ImageNet and well-known benchmark datasets. Additionally, we delve into several noteworthy research directions in NAS methods including one/two-stage NAS, one-shot NAS and joint hyperparameter with architecture optimization. We discussed how the search space size and complexity in NAS can vary depending on the specific problem being addressed. To conclude, we examine several open problems (SOTA problems) within current AutoML methods that assure further investigation in future research.

With the increasing popularity of civilian unmanned aerial vehicles (UAVs), safety issues arising from unsafe operations and terrorist activities have received growing attention. To address this problem, an accurate classification and positioning system is needed. Considering that UAVs usually use radio frequency (RF) signals for video transmission, in this paper, we design a passive distributed monitoring system that can classify and locate UAVs according to their RF signals. Specifically, three passive receivers are arranged in different locations to receive RF signals. Due to the noncooperation between a UAV and receivers, it is necessary to detect whether there is a UAV signal from the received signals. Hence, convolutional neural network (CNN) is proposed to not only detect the presence of the UAV, but also classify its type. After the UAV signal is detected, the time difference of arrival (TDOA) of the UAV signal arriving at the receiver is estimated by the cross-correlation method to obtain the corresponding distance difference. Finally, the Chan algorithm is used to calculate the location of the UAV. We deploy a distributed system constructed by three software defined radio (SDR) receivers on the campus playground, and conduct extensive experiments in a real wireless environment. The experimental results have successfully validated the proposed system.

Deep neural networks (DNNs) are widely used in real-world applications, thanks to their exceptional performance in image recognition. However, their vulnerability to attacks, such as Trojan and data poison, can compromise the integrity and stability of DNN applications. Therefore, it is crucial to verify the integrity of DNN models to ensure their security. Previous research on model watermarking for integrity detection has encountered the issue of overexposure of model parameters during embedding and extraction of the watermark. To address this problem, we propose a novel score-based black-box DNN fragile watermarking framework called fragile trigger generation (FTG). The FTG framework only requires the prediction probability distribution of the final output of the classifier during the watermarking process. It generates different fragile samples as the trigger, based on the classification prediction probability of the target classifier and a specified prediction probability mask to watermark it. Different prediction probability masks can promote the generation of fragile samples in corresponding distribution types. The whole watermarking process does not affect the performance of the target classifier. When verifying the watermarking information, the FTG only needs to compare the prediction results of the model on the samples with the previous label. As a result, the required model parameter information is reduced, and the FTG only needs a few samples to detect slight modifications in the model. Experimental results demonstrate the effectiveness of our proposed method and show its superiority over related work. The FTG framework provides a robust solution for verifying the integrity of DNN models, and its effectiveness in detecting slight modifications makes it a valuable tool for ensuring the security and stability of DNN applications.

The development of information technology has propelled technological reform in artificial intelligence (AI). To address the needs of diversified and complex applications, AI has been increasingly trending towards intelligent, collaborative, and systematized development across different levels and tasks. Research on intelligent, collaborative and systematized AI can be divided into three levels: micro, meso, and macro. Firstly, the micro-level collaboration is illustrated through the introduction of swarm intelligence collaborative methods related to individuals collaboration and decision variables collaboration. Secondly, the meso-level collaboration is discussed in terms of multi-task collaboration and multi-party collaboration. Thirdly, the macro-level collaboration is primarily in the context of intelligent collaborative systems, such as terrestrial-satellite collaboration, space-air-ground collaboration, space-air-ground-air collaboration, vehicle-road-cloud collaboration and end-edge-cloud collaboration. Finally, this paper provides prospects on the future development of relevant fields from the perspectives of the micro, meso, and macro levels.

In this paper, we study turbo codes from the digital signal processing point of view by defining turbo codes over the complex field. It is known that iterative decoding and interleaving between concatenated parallel codes are two key elements that make turbo codes perform significantly better than the conventional error control codes. This is analytically illustrated in this paper. We show that the decoded noise mean power in the iterative decoding decreases when the number of iterations increases, as long as the interleaving decorrelates the noise after each iterative decoding step. An analytic decreasing rate and the limit of the decoded noise mean power are given. The limit of the decoded noise mean power of the iterative decoding of a turbo code with two parallel codes with their rates less than 1/2 is one third of the noise power before the decoding, which can not be achieved by any non-turbo codes with the same rate. From this study, the role of designing a good interleaver can also be clearly seen.

Autoencoder-based rating prediction methods with external attributes have received wide attention due to their ability to accurately capture users' preferences. However, existing methods still have two significant limitations: i) External attributes are often unavailable in the real world due to privacy issues, leading to low quality of representations; and ii) existing methods lack considering complex associations in users' rating behaviors during the encoding process. To meet these challenges, this paper innovatively proposes an inherent-attribute-aware dual-graph autoencoder, named IADGAE, for rating prediction. To address the low quality of representations due to the unavailability of external attributes, we propose an inherent attribute perception module that mines inductive user active patterns and item popularity patterns from users' rating behaviors to strengthen user and item representations. To exploit the complex associations hidden in users’ rating behaviors, we design an encoder on the item-item co-occurrence graph to capture the co-occurrence frequency features among items. Moreover, we propose a dual-graph feature encoder framework to simultaneously encode and fuse the high-order representations learned from the user-item rating graph and item-item co-occurrence graph. Extensive experiments on three real datasets demonstrate that IADGAE is effective and outperforms existing rating prediction methods, which achieves a significant improvement of 4.51%∼41.63 ​% in the RMSE metric.