IEEE Transactions on Information Forensics and Security最新文献

英文中文

Fine-Grained Domain Alignment for Face Anti-Spoofing With Asymmetric Pseudo-Labels 非对称伪标签人脸抗欺骗的细粒度域对齐

IF 8 1区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

IEEE Transactions on Information Forensics and Security

Pub Date : 2026-01-22 DOI: 10.1109/TIFS.2026.3657032

Jing Yang;Xusheng Cui;Yuehai Chen;Shaoyi Du;Badong Chen;Yuewen Liu

As face recognition systems become more prevalent and various presentation attacks continue to surface, the significance of face anti-spoofing (FAS) has escalated. In real-world scenarios, we can utilize the existing labeled sample sets, and we can also obtain a wide range of unlabeled face samples, which are the target samples that we need to classify. However, the existing cross-domain FAS methods do not fully utilize the target domain data. That is, they only align the overall distribution of features shared by the source and target domains, but cannot complete the alignment of live and spoof features relevant to classification within the source and target domains, resulting in not so good generalization performance in cross-domain scenarios, especially when the target domain is more complex compared to the source domain. To address this issue, we propose a novel domain adaptation approach called Fine-Grained Domain Alignment for Face Anti-Spoofing with Asymmetric Pseudo-Labels (FGDA-APL). In this approach, we initially employ traditional domain alignment methods to achieve preliminary domain alignment, which can be considered as coarse-grained domain alignment. Subsequently, we introduce the Multi-Graph Convolutional Network (MGCN) module, which is utilized to generate asymmetric feature spaces and facilitate cross-supervised pseudo-labels for asymmetric pseudo-labels utilization. Within the MGCN module, features extracted by the feature extractor are guided to achieve feature aggregation, resulting in multiple distinct feature spaces. We hypothesize that pseudo-labels with high confidence in these asymmetric feature spaces can be regarded as reliable pseudo-labels. By cross-supervising the pseudo-labels generated by both the classifier and the MGCN, we ultimately achieve alignment and classification of real and spoofing features within both the source and target domains. Consequently, we achieve superior classification performance on target domain data. Our proposed method has demonstrated state-of-the-art performance across multiple public datasets through extensive experiments.

随着人脸识别系统的日益普及和各种表示攻击的不断出现，人脸反欺骗（FAS）的重要性不断提升。在现实场景中，我们既可以利用已有的标记样本集，也可以得到大量未标记的人脸样本，这些样本就是我们需要分类的目标样本。然而，现有的跨域FAS方法并没有充分利用目标域的数据。也就是说，它们只对齐源域和目标域共享的特征的总体分布，而不能完成源域和目标域中与分类相关的活特征和欺骗特征的对齐，导致跨域场景下的泛化性能不太好，特别是当目标域比源域更复杂时。为了解决这个问题，我们提出了一种新的领域自适应方法，称为非对称伪标签面部抗欺骗的细粒度领域对齐（FGDA-APL）。在该方法中，我们首先采用传统的领域对齐方法来实现初步的领域对齐，这可以被认为是粗粒度的领域对齐。随后，我们引入了多图卷积网络（Multi-Graph Convolutional Network， MGCN）模块，利用该模块生成非对称特征空间，并为非对称伪标签的利用提供交叉监督伪标签。在MGCN模块中，引导特征提取器提取的特征进行特征聚合，形成多个不同的特征空间。我们假设在这些非对称特征空间中具有高置信度的伪标签可以视为可靠的伪标签。通过交叉监督由分类器和MGCN生成的伪标签，我们最终实现了源和目标域中真实特征和欺骗特征的对齐和分类。因此，我们在目标域数据上取得了优异的分类性能。通过广泛的实验，我们提出的方法在多个公共数据集上展示了最先进的性能。

{"title":"Fine-Grained Domain Alignment for Face Anti-Spoofing With Asymmetric Pseudo-Labels","authors":"Jing Yang;Xusheng Cui;Yuehai Chen;Shaoyi Du;Badong Chen;Yuewen Liu","doi":"10.1109/TIFS.2026.3657032","DOIUrl":"10.1109/TIFS.2026.3657032","url":null,"abstract":"As face recognition systems become more prevalent and various presentation attacks continue to surface, the significance of face anti-spoofing (FAS) has escalated. In real-world scenarios, we can utilize the existing labeled sample sets, and we can also obtain a wide range of unlabeled face samples, which are the target samples that we need to classify. However, the existing cross-domain FAS methods do not fully utilize the target domain data. That is, they only align the overall distribution of features shared by the source and target domains, but cannot complete the alignment of live and spoof features relevant to classification within the source and target domains, resulting in not so good generalization performance in cross-domain scenarios, especially when the target domain is more complex compared to the source domain. To address this issue, we propose a novel domain adaptation approach called Fine-Grained Domain Alignment for Face Anti-Spoofing with Asymmetric Pseudo-Labels (FGDA-APL). In this approach, we initially employ traditional domain alignment methods to achieve preliminary domain alignment, which can be considered as coarse-grained domain alignment. Subsequently, we introduce the Multi-Graph Convolutional Network (MGCN) module, which is utilized to generate asymmetric feature spaces and facilitate cross-supervised pseudo-labels for asymmetric pseudo-labels utilization. Within the MGCN module, features extracted by the feature extractor are guided to achieve feature aggregation, resulting in multiple distinct feature spaces. We hypothesize that pseudo-labels with high confidence in these asymmetric feature spaces can be regarded as reliable pseudo-labels. By cross-supervising the pseudo-labels generated by both the classifier and the MGCN, we ultimately achieve alignment and classification of real and spoofing features within both the source and target domains. Consequently, we achieve superior classification performance on target domain data. Our proposed method has demonstrated state-of-the-art performance across multiple public datasets through extensive experiments.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"1973-1986"},"PeriodicalIF":8.0,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SALUS: Large-Scale Homomorphic Circuit Synthesis via Logic-Aware LUT Optimization 基于逻辑感知LUT优化的大规模同态电路合成

IF 8 1区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

IEEE Transactions on Information Forensics and Security

Pub Date : 2026-01-22 DOI: 10.1109/TIFS.2026.3657090

Ran Mao;Zhou Zhang;Zian Zhao;Zhenyu Guan;Peng Yin;Song Bian

Recently, growing interests are developed in optimizing fully homomorphic encryption (FHE) circuits to enable Boolean function evaluations over ciphertexts. While existing works utilize functional bootstrapping (FBS) to efficiently evaluate logic gates, the evaluation efficiency for large-scale circuits remains limited. Recent advances introduce a fast ciphertext conversion method, making it feasible to evaluate look-up tables (LUTs) over homomorphic multiplexer operation. In this work, we propose a new circuit synthesis framework, SALUS, which automatically generates and evaluates gate-level graphs over homomorphic LUTs given an input Boolean circuit. We apply the binary decision diagram (BDD) reordering method and multi-value refresh techniques to efficiently evaluate complex LUTs. Additionally, we propose a heuristic algorithm to merge LUTs in a given circuit into multi-output LUTs. In the experiments, we examine the efficiency of SALUS using a wide range of benchmark suites, including the EPFL and ISCAS benchmark circuits. We show that SALUS achieves a maximum reduction of up to

$26times $

in computational latency compared to state-of-the-art homomorphic circuit synthesis method. Furthermore, we evaluate real-world applications, e.g., image filtering and matrix multiplication, and achieve an average speedup of

$8.6times $

(with a maximum speedup of

$24times $

) compared to the FBS-based method.

近年来，人们对优化完全同态加密（FHE）电路以实现对密文的布尔函数求值越来越感兴趣。虽然现有的工作利用功能自举（FBS）来有效地评估逻辑门，但大规模电路的评估效率仍然有限。最近的进展引入了一种快速的密文转换方法，使得对同态多路复用器操作的查找表（lut）进行评估成为可能。在这项工作中，我们提出了一个新的电路合成框架，SALUS，它在给定输入布尔电路的同态lut上自动生成和评估门级图。我们应用二元决策图（BDD）重排序方法和多值刷新技术对复杂lut进行高效的评估。此外，我们提出了一种启发式算法，将给定电路中的lut合并为多输出lut。在实验中，我们使用广泛的基准套件来检查SALUS的效率，包括EPFL和ISCAS基准电路。我们表明，与最先进的同态电路合成方法相比，SALUS在计算延迟方面最大减少了26倍。此外，我们评估了现实世界的应用，例如图像滤波和矩阵乘法，与基于fbs的方法相比，实现了8.6倍的平均加速（最大加速为24倍）。

{"title":"SALUS: Large-Scale Homomorphic Circuit Synthesis via Logic-Aware LUT Optimization","authors":"Ran Mao;Zhou Zhang;Zian Zhao;Zhenyu Guan;Peng Yin;Song Bian","doi":"10.1109/TIFS.2026.3657090","DOIUrl":"10.1109/TIFS.2026.3657090","url":null,"abstract":"Recently, growing interests are developed in optimizing fully homomorphic encryption (FHE) circuits to enable Boolean function evaluations over ciphertexts. While existing works utilize functional bootstrapping (FBS) to efficiently evaluate logic gates, the evaluation efficiency for large-scale circuits remains limited. Recent advances introduce a fast ciphertext conversion method, making it feasible to evaluate look-up tables (LUTs) over homomorphic multiplexer operation. In this work, we propose a new circuit synthesis framework, SALUS, which automatically generates and evaluates gate-level graphs over homomorphic LUTs given an input Boolean circuit. We apply the binary decision diagram (BDD) reordering method and multi-value refresh techniques to efficiently evaluate complex LUTs. Additionally, we propose a heuristic algorithm to merge LUTs in a given circuit into multi-output LUTs. In the experiments, we examine the efficiency of SALUS using a wide range of benchmark suites, including the EPFL and ISCAS benchmark circuits. We show that SALUS achieves a maximum reduction of up to <inline-formula> <tex-math>$26times $ </tex-math></inline-formula> in computational latency compared to state-of-the-art homomorphic circuit synthesis method. Furthermore, we evaluate real-world applications, e.g., image filtering and matrix multiplication, and achieve an average speedup of <inline-formula> <tex-math>$8.6times $ </tex-math></inline-formula> (with a maximum speedup of <inline-formula> <tex-math>$24times $ </tex-math></inline-formula>) compared to the FBS-based method.","PeriodicalId":13492,"journal":{"name":"IEEE Transactions on Information Forensics and Security","volume":"21 ","pages":"2002-2016"},"PeriodicalIF":8.0,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146043077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adversarial Video Promotion Against Text-to-Video Retrieval 对抗性视频推广对抗文本到视频检索