Abstract
Deepfake technologies are evolving rapidly, the malicious or illegal uses of deepfakes have raised serious threats in societal, political, and business fields. To tackle such threats, the latest and most effective methods combine the advantages of vision transformer and CNN to detect deepfakes. However, deploying the deepfake detection networks on the existing CNN and transformer accelerators faces several critical issues such as the inefficiency and underutilization. We propose a novel accelerator architecture for deepfake detection networks, FakeGuard, which enables a cost-effective, high performance hybrid network execution. It features a flexible computing engine with reconfigurable adder tree to support for different computing patterns within a single hardware architecture. A fine-grained, dependency-free task scheduling mechanism is designed to maximize hardware resources utilization. Extensive experiments show that FakeGuard surpasses the state-of-art accelerators.
Supported by National Natural Science Foundation of China: No. 62272459 and No. 62125208.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Karras, T., et al.: Analyzing and improving the image quality of stylegan. In: CVPR (2020)
Mallya, A., et al.: Implicit warping for animation with image sets. In: NeurIPS (2022)
Shao, R., et al.: Detecting and grounding multi-modal media manipulation. In: CVPR, pp. 6904–6913 (2023)
Touvron, H., et al.: Llama: open and efficient foundation language models. CoRR (2023)
Zellers, R., et al.: Defending against neural fake news. In: NeurIPS (2019)
Chesney, B., et al.: Deep fakes: a looming challenge for privacy, democracy, and national security. Calif. L. Rev. 107, 1753 (2019)
Lin, H., et al.: Improved xception with dual attention mechanism and feature fusion for face forgery detection. In: ICDIS (2022)
Das, S., et al.: Towards solving the deepfake problem: an analysis on improving deepfake detection using dynamic face augmentation. In: CVPR (2021)
Shah, D., et al.: Xception net and vision transformer: a comparative study for deepfake detection. In: MLCSS. IEEE (2022)
Liu, T., et al.: Identification of fake stereo audio using SVM and CNN. Information 12, 263 (2021)
Wodajo, D., et al.: Deepfake video detection using convolutional vision transformer. arXiv preprint arXiv:2102.11126 (2021)
Kaddar, B., et al.: HCiT: deepfake video detection using a hybrid model of CNN features and vision transformer. In: VCIP, pp. 1–5. IEEE (2021)
Khan, S.A., et al.: Hybrid transformer network for deepfake detection. In: CBMI, pp. 8–14 (2022)
Wang, J., et al.: M2tr: multi-modal multi-scale transformers for deepfake detection. In: ICMR, pp. 615–623 (2022)
Coccomini, D.A., et al.: MINTIME: multi-identity size-invariant video deepfake detection. arXiv preprint arXiv:2211.10996 (2022)
Report: number of expert-crafted video deepfakes double every six months. https://cybernews.com/privacy/
Jouppi, N.P., et al.: In-datacenter performance analysis of a tensor processing unit. In: ISCA, pp. 1–12 (2017)
Lu, L., et al.: Sanger: a co-design framework for enabling sparse attention using reconfigurable architecture. In: MICRO-54, pp. 977–991 (2021)
Samajdar, A., et al.: A systematic methodology for characterizing scalability of DNN accelerators using SCALE-sim. In: ISPASS (2020)
Li, S., et al.: DRAMsim3: a cycle-accurate, thermal-capable DRAM simulator. In: IEEE CAL, vol. 19 (2020)
Li, S., et al.: Cacti-p: architecture-level modeling for sram-based structures with advanced leakage reduction techniques. In: ICCAD 2011 (2011)
You, H., et al.: ViTCoD: vision transformer acceleration via dedicated algorithm and accelerator co-design. In: HPCA (2023)
Li, B., et al.: Ftrans: energy-efficient acceleration of transformers using FPGA. In: ISLOED, pp. 175–180 (2020)
Kwon, H., et al.: MAERI: enabling flexible dataflow mapping over DNN accelerators via reconfigurable interconnects. In: ASPLOS (2018)
Qin, E., et al.: Sigma: a sparse and irregular gemm accelerator with flexible interconnects for dnn training. In: HPCA, pp. 58–70. IEEE (2020)
Qin, Y., et al.: FACT: FFN-attention co-optimized transformer architecture with eager correlation prediction. In: ISCA-50, pp. 1–14 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, X., Meng, D., Hou, R., Wang, Y. (2024). FakeGuard: Novel Architecture Support for Deepfake Detection Networks. In: Carretero, J., Shende, S., Garcia-Blas, J., Brandic, I., Olcoz, K., Schreiber, M. (eds) Euro-Par 2024: Parallel Processing. Euro-Par 2024. Lecture Notes in Computer Science, vol 14802. Springer, Cham. https://doi.org/10.1007/978-3-031-69766-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-69766-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-69765-4
Online ISBN: 978-3-031-69766-1
eBook Packages: Computer ScienceComputer Science (R0)