Detecting fraudulent online text is essential, as these manipulative messages exploit human greed, deceive individuals, and endanger societal security. Currently, this task remains under-explored on the Chinese web due to the lack of a comprehensive dataset of Chinese fraudulent texts. However, creating such a dataset is challenging because it requires extensive annotation within a vast collection of normal texts. Additionally, the creators of fraudulent webpages continuously update their tactics to evade detection by downstream platforms and promote fraudulent messages. To this end, this work firstly presents the comprehensive long-term dataset of Chinese fraudulent texts collected over 12 months, consisting of 59,106 entries extracted from billions of web pages. Furthermore, we design and provide a wide range of baselines, including large language model-based detectors, and pre-trained language model approaches. The necessary dataset and benchmark codes for further research are available via https://github.com/xuemingxxx/ChiFraud.

Traffic congestion is an inevitable issue faced by urban cities due to the high population density and transportation requirements. Although public transport and infrastructure improvements can alleviate congestion, spatial limitations restrict these solutions. Therefore, an additional system is necessary to mitigate traffic congestion on existing, overburdened networks. Currently, researchers are primarily investigating traffic rerouting systems integrated with artificial intelligence to distribute vehicles and optimize road usage with minimal costs. Likewise, this paper proposed a dynamic rerouting system integrated with simple artificial intelligence that consists of near-future traffic flow prediction while also introducing a Key Performance Index (KPI) to accurately measure congestion levels and effectively select vehicles for rerouting with minimum cost. The proposed system first aggregates various traffic data to serve as the input of a Support Vector Machine (SVM) traffic flow prediction model, which estimates near-future traffic conditions. These conditions are then measured using a self-proposed KPI to label the congestion level of each road. A vehicle filtration process then selects the vehicles for rerouting based on the congestion level and the travel cost between the origin and destination. Finally, an alternative route is computed via a k Shortest Path (kSP) model by minimizing the travel time. Simulation results indicate that the proposed vehicle rerouting system is capable of reducing the total travel time of a given traffic network by an astonishing 33.1 %. • Proposed a near real-time rerouting system with the aim of reducing the total travel time of a traffic network. • Introduced an innovative Key Performance Index system that accurately assesses the congestion level for the rerouting system. • Minimizing the cost of rerouting via a vehicle filtration process to minimize the number of rerouted vehicles. • Applied Support Vector Machine to perform near-future traffic flow prediction to achieve proactive rerouting. • Investigated the effects of rerouting intervals, traffic levels and Key Performance Index weightages on the proposed system.

Feature distillation is a widely used training method to transfer feature information from a teacher to a student network. Current methods seek to minimize the reconstruction error of hidden feature maps between teacher-student models by explicitly optimizing distillation loss. However, some feature loss methods require complex transformations, which are not easy to optimize. In this paper, we propose a novel and effective feature distillation method, which learns to transfer knowledge by applying feature fusion as an alternative to distillation loss. Specifically, we fuse the intermediate feature of the student model to the attention teacher network, which has better representation and relatively less training cost. During training, this separable feature fusion can effectively transfer feature knowledge and is easy to optimize without complex transformation. After training, the feature fusion and the teacher network can be discarded, and the student network can be used separately in inference. Equipped with auxiliary classifier for ensemble logits distillation, our Separable Feature Knowledge Distillation (SFKD) obtains state-of-the-art performance. In experiments, SFKD achieves 4% performance improvement on CIFAR-100 and 2% on ImageNet for ResNet models, which substantially outperforms other feature distillation methods.

Feature distillation always leads to significant performance improvements, but requires extra training budgets. To address the problem, we propose TFD, a simple and effective Teacher-Free Distillation framework, which seeks to reuse the privileged features within the student network itself. Specifically, TFD squeezes feature knowledge in the deeper layers into the shallow ones by minimizing feature loss. Thanks to the narrow gap of these self-features, TFD only needs to adopt a simple l2loss without complex transformations. Extensive experiments on recognition benchmarks show that our framework can achieve superior performance than teacher-based feature distillation methods. On the ImageNet dataset, our approach achieves 0.8% gains for ResNet18, which surpasses other state-of-the-art training techniques.

In this paper, we propose a histogram of oriented gradient inspired cancelable biometrics - Random Augmented Histogram of Gradients (R∙HoG) for iris template protection. The proposed R∙HoG is built upon on two main components: 1) column vector random augmentation and 2) gradient orientation grouping mechanisms to transform the unaligned irisCode feature into the alignment-robust cancelable template. The alignment-robust property of the proposed R∙HoG enables the fast template comparison which is crucial for an efficient authentication process. Experiments were performed on CASIA-IrisV3-Internal and CASIA-IrisV4-Thousand datasets. The results demonstrate the proposed R∙HoG could achieve acceptable verification performance in both datasets. Other than that, the irreversibility and security properties are studied based on major security and privacy attacks in biometric system. Lastly, results from the benchmarking evaluation framework show the proposed method is satisfying the unlinkability property.