Beyond the Pixel World: A Novel Acoustic-Based Face Anti-Spoofing System for Smartphones

Kong, Chenqi; Zheng, Kexin; Wang, Shiqi; Rocha, Anderson; Li, Haoliang

doi:10.1109/tifs.2022.3202115

Cited by 24 publications

(5 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yu et al [51] combines face depth estimation framework [5] and the CDC [6] to fuse multi-modal information and achieved the best results in a FAS competition [52]. Instead of depth and infrared maps, Kong et al [53] devise a novel and costeffective FAS system based on the acoustic modality, named Echo-FAS, which employs the crafted acoustic signal as the probe to perform face liveness detection.…”

Section: Related Workmentioning

confidence: 99%

CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

Liu¹,

Tan

Wan

et al. 2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

121

View full text Add to dashboard Cite

The availability of handy multi-modal (i.e., RGB-D) sensors has brought about a surge of face anti-spoofing research. However, the current multi-modal face presentation attack detection (PAD) has two defects: (1) The framework based on multimodal fusion requires providing modalities consistent with the training input, which seriously limits the deployment scenario.(2) The performance of ConvNet-based model on high fidelity datasets is increasingly limited. In this work, we present a pure transformer-based framework, dubbed the Flexible Modal Vision Transformer (FM-ViT), for face anti-spoofing to flexibly target any single-modal (i.e., RGB) attack scenarios with the help of available multi-modal data. Specifically, FM-ViT retains a specific branch for each modality to capture different modal information and introduces the Cross-Modal Transformer Block (CMTB), which consists of two cascaded attentions named Multi-headed Mutual-Attention (MMA) and Fusion-Attention (MFA) to guide each modal branch to mine potential features from informative patch tokens, and to learn modality-agnostic liveness features by enriching the modal information of own CLS token, respectively. Experiments demonstrate that the single model trained based on FM-ViT can not only flexibly evaluate different modal samples, but also outperforms existing single-modal frameworks by a large margin, and approaches the multi-modal frameworks introduced with smaller FLOPs and model parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

Liu¹,

Tan

Wan

et al. 2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

121

View full text Add to dashboard Cite

show abstract

“…Effective deception detection has crucial implications in the area of border security, anti-fraud, business negotiations and etc. [14,12,1,13,9,27,44]. Deep learning algorithms have achieved comparable or even better performance than human in many complex tasks [22,41,40,7,38].…”

Section: Introductionmentioning

confidence: 99%

Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning

Guo,

Selvaraj,

et al. 2023

2023 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Deception detection in conversations is a challenging yet important task, having pivotal applications in many fields such as credibility assessment in business, multimedia anti-frauds, and custom security. Despite this, deception detection research is hindered by the lack of highquality deception datasets, as well as the difficulties of learning multimodal features effectively. To address this issue, we introduce DOLOS 1 , the largest gameshow deception detection dataset with rich deceptive conversations. DOLOS includes 1,675 video clips featuring 213 subjects, and it has been labeled with audio-visual feature annotations. We provide train-test, duration, and gender protocols to investigate the impact of different factors. We benchmark our dataset on previously proposed deception detection approaches. To further improve the performance by fine-tuning fewer parameters, we propose Parameter-Efficient Crossmodal Learning (PECL), where a Uniform Temporal Adapter (UT-Adapter) explores temporal attention in transformer-based architectures, and a crossmodal fusion module, Plug-in Audio-Visual Fusion (PAVF), combines crossmodal information from audio-visual features. Based on the rich fine-grained audio-visual annotations on DOLOS, we also exploit multi-task learning to enhance performance by concurrently predicting deception and audiovisual features. Experimental results demonstrate the desired quality of the DOLOS dataset and the effectiveness of the PECL. The DOLOS dataset and the source codes are available at here.

show abstract

“…Together with the impressive performance of the deep neural networks, many concerns have been raised about their related AI security issues [23,54]. Primarily due to the lack of transparency in deep neural networks, it is observed that a variety of attacks can compromise the deployment and reliability of AI systems [24,25,53] in computer vision, natural language processing, speech recognition, etc. Among all these attacks, backdoor attacks have recently attracted lots of attention.…”

Section: Introductionmentioning

confidence: 99%

Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger

Yu,

Wang,

Yang

et al. 2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable to backdoor attacks, where some specific trigger patterns added to the input can lead to malicious behavior of the models. In this paper, we present a novel backdoor attack with multiple triggers against learned image compression models. Motivated by the widely used discrete cosine transform (DCT) in existing compression systems and standards, we propose a frequency-based trigger injection model that adds triggers in the DCT domain. In particular, we design several attack objectives for various attacking scenarios, including: 1) attacking compression quality in terms of bit-rate and reconstruction quality; 2) attacking task-driven measures, such as down-stream face recognition and semantic segmentation. Moreover, a novel simple dynamic loss is designed to balance the influence of different loss terms adaptively, which helps achieve more efficient training. Extensive experiments show that with our trained trigger injection models and simple modification of encoder parameters (of the compression model), the proposed attack can successfully inject several backdoors with corresponding triggers in a single image compression model.

show abstract

Beyond the Pixel World: A Novel Acoustic-Based Face Anti-Spoofing System for Smartphones

Cited by 24 publications

References 57 publications

CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing

Audio-Visual Deception Detection: DOLOS Dataset and Parameter-Efficient Crossmodal Learning

Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger

Contact Info

Product

Resources

About