Heterogeneous fraud detection is an important means of credit card security assurance, which can utilize historical transaction records in a source and target domain to build an effective fraud detection model. Nevertheless, large feature distribution differences between source and target transaction instances and the complex intrinsic structure hidden behind transaction data make it difficult for existing credit card fraud detection (CCFD) models to capture and transfer the most informative feature representations and seriously hinder detection performance. In this work, we propose a novel adaptive heterogeneous CCFD model named RTAHC based on deep reinforcement training subset selection, which mainly contains two components: selection distribution generator (SDG) and transaction fraud detector (TFD, including feature extractor with an attention mechanism and classifier). The SDG can generate the selection probability distribution vector via the reinforcement reward mechanism, and then transaction instances in the source domain relevant to the target domain are selected. The feature extractor with an attention mechanism can learn the abstract deep semantic feature representations of selected source transaction instances and the target domain. The joint training of SDG and TFD can provide more real-time and accurate transaction feature representations to reduce the distribution discrepancy between the two domains. We verify the detection performance of RTAHC across a large real-world credit card transaction dataset and four public datasets. Experimental results demonstrate that the RTAHC model can exhibit competitive CCFD performance.
5 February 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Although various video saliency models have achieved considerable performance gains, existing deep learning-based audio-visual saliency prediction models are still in the early exploration stage. The major challenge is that there are relatively few audio-visual sequences with real human eye fixations collected under the audio-visual circumstance. To this end, this paper presents a novel multi-modal transformer-based class activation mapping (MTCAM) model in a weakly-supervised training manner to effectively alleviate the need of large-scale datasets for audio-visual saliency prediction. In particular, by using only video category labels in the video classification task, we propose to employ the class activation mapping based on multi-modal transformer, which follows a two-stage training methodology to extract the most discriminative regions. Such regions with strong discriminative ability are highly consistent with real human eye fixations. Meanwhile, we further devise an efficient feature reuse mechanism to reduce redundant computation and enable previously obtained features can provide effective guidance for downstream model learning. It is particularly noteworthy that this work is the first attempt to exploit the cross-modal transformer to focus on cross-modal interaction at the entire video and predict human eye fixations in a weakly-supervised training strategy. We conduct extensive experiments on several benchmark datasets to demonstrate that the proposed MTCAM model significantly outperforms other competitors. Furthermore, detailed ablation experiments are also performed to validate the effectiveness and rationality of each component in our proposed model.
28 September 2023 in Software: Practice and Experience
In the era of deep learning, audio-visual saliency prediction is still in its infancy due to the complexity of video signals and the continuous correlation in the temporal dimension. Most existing approaches treat videos as 3D grids of RGB values and model them using discrete neural networks, leading to issues such as video content-agnostic and sub-optimal feature representation ability. To address these challenges, we propose a novel dynamic-aware audio-visual saliency (DAVS) model based on implicit neural representations (INRs). The core of our proposed DAVS model is to build an effective mapping by exploiting a parametric neural network that maps space-time coordinates to the corresponding saliency values. Specifically, our model incorporates an INR-based video generator that decomposes videos into image, motion, and audio feature vectors, learning video content-adaptive features via a parametric neural network. This generator efficiently encodes videos, naturally models continuous temporal dynamics, and enhances feature representation capability. Furthermore, we introduce a parametric audio-visual feature fusion strategy in the saliency prediction procedure, enabling intrinsic interactions between modalities and adaptively integrating visual and audio cues. Through extensive experiments on benchmark datasets, our proposed DAVS model demonstrates promising performance and intriguing properties in audio-visual saliency prediction.
Fraud detection on dynamic graph (FDDG) is in high demand across many real-world applications, such as financial transaction networks and social networks. A graph neural network (GNN) is an advanced methodology for learning graph data and has been widely adopted in fraud detection tasks. Despite the promising results, research on GNN-based fraud detection faces two critical challenges. First, due to the lack of temporal consistency mining in existing methods, camouflaged fraudsters can easily evade detection by imitating the behavioral patterns of benign users. Second, with constantly evolving fraud patterns and a scarcity of fraud samples, existing methods can easily overfit to current fraud patterns and struggle to identify the evolved and new ones. To address these challenges, we propose CamFD, a semi-supervised camouflage-aware fraud detection model on dynamic graphs. To detect the temporal inconsistency in the behavioral patterns of camouflaged fraudsters, CamFD is equipped with a novel consistency-sensitive contrastive learning (CSCL) module. CSCL discriminatively learns the consistency and inconsistency in users’ behavioral patterns by constructing temporal and structural contrastive pairs. Since modeling the evolving fraud patterns with sparse fraud samples is almost impractical, CamFD concentrates on modeling the relatively stable patterns of extensive benign users with a multivariate Gaussian distribution modeling (MGDM) module. We conduct extensive experiments on a private credit card fraud dataset as well as three public datasets. The experimental results demonstrate that CamFD outperforms ten state-of-the-art (SOTA) baselines across all datasets, with the area under ROC curve (AUC) improvements ranging from 1.03% to 5.32%.