arXiv subjects

Tingting Song

Publications and source records attributed to Tingting Song.

8 recordsLinked to original sources

arXiv2026

REIMU: Efficient Heterogeneous Hierarchical Reasoning for SSL-Based Speech Deepfake Detection

The increasing realism of speech generated by text-to-speech and voice conversion systems poses growing challenges to media integrity and voice authentication. Self-supervised learning (SSL) has substantially advanced speech deepfake detection, where downstream backbones conventionally process SSL representations through a single forward pass. This work investigates the practical effectiveness of recurrent hierarchical reasoning for this task. We term this controlled study REIMU and systematically compare conventional single-pass backbones, weight-shared recurrence, homogeneous HRM, and heterogeneous HRM across four Base-scale SSL frontends. We further examine heterogeneous high- and low-level modules that combine self-attention with linear attention. Experiments on the ASVspoof 2019 and 2021 evaluation sets show that recurrence and hierarchical decomposition do not inherently improve detection, whereas heterogeneous operator assignment provides a more competitive configuration. Notably, the heterogeneous design remains competitive while using 10.8\% fewer downstream parameters than the matched baseline, demonstrating its potential for parameter-efficient speech deepfake detection.

eess.AS↗

arXiv2026

XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection

Advanced speech synthesis technologies have enabled highly realistic speech generation, posing security risks that motivate research into audio deepfake detection (ADD). While state space models (SSMs) offer linear complexity, pure causal SSMs architectures often struggle with the content-based retrieval required to capture global frequency-domain artifacts. To address this, we explore the scaling properties of hybrid architectures by proposing XLSR-MamBo, a modular framework integrating an XLSR front-end with synergistic Mamba-Attention backbones. We systematically evaluate four topological designs using advanced SSM variants, Mamba, Mamba2, Hydra, and Gated DeltaNet. Experimental results demonstrate that the MamBo-3-Hydra-N3 configuration achieves competitive performance compared to other state-of-the-art systems on the ASVspoof 2021 LA, DF, and In-the-Wild benchmarks. This performance benefits from Hydra's native bidirectional modeling, which captures holistic temporal dependencies more efficiently than the heuristic dual-branch strategies employed in prior works. Furthermore, evaluations on the DFADD dataset demonstrate robust generalization to unseen diffusion- and flow-matching-based synthesis methods. Crucially, our analysis reveals that scaling backbone depth effectively mitigates the performance variance and instability observed in shallower models. These results demonstrate the hybrid framework's ability to capture artifacts in spoofed speech signals, providing an effective method for ADD.

eess.AS↗

arXiv2025

AI-Driven Prediction of Cancer Pain Episodes: A Hybrid Decision Support Approach

Lung cancer patients frequently experience breakthrough pain episodes, with up to 91% requiring timely intervention. To enable proactive pain management, we propose a hybrid machine learning and large language model pipeline that predicts pain episodes within 48 and 72 hours of hospitalization using both structured and unstructured electronic health record data. A retrospective cohort of 266 inpatients was analyzed, with features including demographics, tumor stage, vital signs, and WHO-tiered analgesic use. The machine learning module captured temporal medication trends, while the large language model interpreted ambiguous dosing records and free-text clinical notes. Integrating these modalities improved sensitivity and interpretability. Our framework achieved an accuracy of 0.876 (48h) and 0.917 (72h), with improvements in sensitivity of 10.6% and 10.7%, respectively, attributable to large language model augmentation. This hybrid approach offers a clinically interpretable and scalable tool for early pain episode forecasting, with potential to enhance treatment precision and optimize resource allocation in oncology care.

cs.AI↗

arXiv2024

Hybrid Quantum-Classical Convolutional Neural Networks for Image Classification in Multiple Color Spaces

The growing complexity and scale of image processing tasks challenge classical convolutional neural networks (CNNs) with high computational costs. Hybrid quantum-classical convolutional neural networks (HQCNNs) show potential to improve performance by accelerating processing speed, enhancing classification accuracy, and reducing model parameters, though studies have primarily focused on the RGB color space. However, the effectiveness of HQCNNs in non-RGB color spaces, such as Lab, YCrCb, and HSV, remains largely unexplored. We propose an HQCNN to evaluate image classification across diverse color spaces. The HQCNN integrates parameterized quantum circuits (PQCs) with a classical CNN, leveraging quantum entanglement and trainable gates to enhance expressiveness across varied color representations. We assess performance on MNIST, CIFAR-10, EuroSAT, and SAT-4 datasets. Experimental results demonstrate that the HQCNN outperforms the classical CNN across all tested color spaces for the ten-class MNIST task, achieving a best accuracy of $94.3\%$ in Lab compared to $92.8\%$ in RGB for the CNN, with superior performance on other datasets in various color spaces. These findings highlight the potential of non-RGB color spaces and optimized PQC designs to improve classification performance. We provide new insights for advancing hybrid quantum-classical computer vision through optimized PQC architectures and diverse color space applications.

quant-ph↗

arXiv2023

LDConv: Linear deformable convolution for improving convolutional neural networks

Neural networks based on convolutional operations have achieved remarkable results in the field of deep learning, but there are two inherent flaws in standard convolutional operations. On the one hand, the convolution operation is confined to a local window, so it cannot capture information from other locations, and its sampled shapes is fixed. On the other hand, the size of the convolutional kernel are fixed to k $\times$ k, which is a fixed square shape, and the number of parameters tends to grow squarely with size. Although Deformable Convolution (Deformable Conv) address the problem of fixed sampling of standard convolutions, the number of parameters also tends to grow in a squared manner. In response to the above questions, the Linear Deformable Convolution (LDConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance. In LDConv, a novel coordinate generation algorithm is defined to generate different initial sampled positions for convolutional kernels of arbitrary size. To adapt to changing targets, offsets are introduced to adjust the shape of the samples at each position. LDConv corrects the growth trend of the number of parameters for standard convolution and Deformable Conv to a linear growth. Moreover, it completes the process of efficient feature extraction by irregular convolutional operations and brings more exploration options for convolutional sampled shapes. Object detection experiments on representative datasets COCO2017, VOC 7+12, and VisDrone-DET2021 fully demonstrate the advantages of LDConv. LDConv is a plug-and-play convolutional operation that can replace the convolutional operation to improve network performance. The code for the relevant tasks can be found at https://github.com/CV-ZhangXin/LDConv.

cs.CV↗

arXiv2023

RFAConv: Receptive-Field Attention Convolution for Improving Convolutional Neural Networks

In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked. This work delves into the mechanism of spatial attention and reveals a new insight. It is that the mechanism essentially addresses the issue of convolutional parameter sharing. By addressing this issue, the convolutional kernel can efficiently extract features by employing varying weights at distinct locations. However, current spatial attention mechanisms focus on shallow attention to spatial features, which is insufficient to address the fundamental challenge of parameter sharing in convolutions involving larger kernels. In response to this challenge, we introduce a novel attention mechanism known as Receptive-Field Attention (RFA). Compared to existing spatial attention methods, RFA not only concentrates on the receptive-field spatial features but also offers effective attention weights for large convolutional kernels. Building upon the RFA concept, a Receptive-Field Attention Convolution (RFAConv) is proposed to supplant the conventional standard convolution. Notably, it offers nearly negligible increment of computational overhead and parameters, while significantly improving network performance. Furthermore, this work reveals that current spatial attention mechanisms require enhanced prioritization of receptive-field spatial features to optimize network performance. To validate the advantages of the proposed methods, we conduct many experiments across several authoritative datasets, including ImageNet, COCO, VOC, and Roboflow...

cs.CV↗

arXiv2021

Selective hydrogenation improves interface properties of high-k dielectrics on 2D semiconductors

The integration of high-k dielectrics with two-dimensional (2D) semiconductors is a critical step towards high-performance nanoelectronics, which however remains challenging due to high density of interface states and the damage to the monolayer 2D semiconductors. In this study, we propose a selective hydrogenation strategy to improve the interface properties while do not affect the 2D semiconductors. Using the interface of monolayer MoS2 and silicon nitride as an example, we show substantially improved interface properties for electronic applications after the interfacial hydrogenation, as evidenced by reduced inhomogeneous charge redistribution, increased band offset, and untouched electronic properties of MoS2. Interestingly, this hydrogenation process selectively occurs only at the silicon nitride surface and is compatible with the current semiconductor fabrication process. We further show that this strategy is general and applicable to other interfaces between high-k dielectrics and 2D semiconductors such as HfO2 on the monolayer MoS2. Our results demonstrate a simple yet viable way to improve the interfacial properties for integrating many high-k dielectrics on a broad range of two-dimensional transition metal disulfide semiconductors.

cond-mat.mtrl-sci↗

arXiv2019

Enhancing JPEG Steganography using Iterative Adversarial Examples

Convolutional Neural Networks (CNN) based methods have significantly improved the performance of image steganalysis compared with conventional ones based on hand-crafted features. However, many existing literatures on computer vision have pointed out that those effective CNN-based methods can be easily fooled by adversarial examples. In this paper, we propose a novel steganography framework based on adversarial example in an iterative manner. The proposed framework first starts from an existing embedding cost, such as J-UNIWARD in this work, and then updates the cost iteratively based on adversarial examples derived from a series of steganalytic networks until achieving satisfactory results. We carefully analyze two important factors that would affect the security performance of the proposed framework, i.e. the percentage of selected gradients with larger amplitude and the adversarial intensity to modify embedding cost. The experimental results evaluated on three modern steganalytic models, including GFR, SCA-GFR and SRNet, show that the proposed framework is very promising to enhance the security performances of JPEG steganography.

cs.MM↗