Lune

CVPR2021Top-tier venue

Improving the Efficiency and Robustness of Deepfakes Detection Through Precise Geometric Features

Zekun Sun, Yujie Han, Zeyu Hua, Na Ruan, Weijia Jia

Abstract

Deepfakes is a branch of malicious techniques that transplant a target face to the original one in videos, resulting in serious problems such as infringement of copyright, confusion of information, or even public panic. Previous efforts for Deepfakes videos detection mainly focused on appearance features, which have a risk of being bypassed by sophisticated manipulation, also resulting in high model complexity and sensitiveness to noise. Besides, how to mine the temporal features of manipulated videos and exploit them is still an open question. We propose an efficient and robust framework named LRNet for detecting Deepfakes videos through temporal modeling on precise geometric features. A novel calibration module is devised to enhance the precision of geometric features, making it more discriminative, and a two-stream Recurrent Neural Network (RNN) is constructed for sufficient exploitation of temporal features. Compared to previous methods, our proposed method is lighter-weighted and easier to train. Moreover, our method has shown robustness in detecting highly compressed or noise corrupted videos. Our model achieved 0.999 AUC on FaceForensics++ dataset. Meanwhile, it has a graceful decline in performance (-0.042 AUC) when faced with highly compressed videos. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

18 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Face X-Ray for More General Face Forgery Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
  • DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
  • Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection cites Face X-Ray for More General Face Forgery Detection
  • Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection cites DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
  • Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
  • Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection cites Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
  • OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training cites Face X-Ray for More General Face Forgery Detection
  • OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training cites DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
  • OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training cites FaceForensics++: Learning to Detect Manipulated Facial Images
  • OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training cites Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
  • OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training cites Exploring Frequency Adversarial Attacks for Face Forgery Detection
  • Exploring Frequency Adversarial Attacks for Face Forgery Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
  • Delving into Sequential Patches for Deepfake Detection cites Face X-Ray for More General Face Forgery Detection
  • Delving into Sequential Patches for Deepfake Detection cites DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
  • Delving into Sequential Patches for Deepfake Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
  • Delving into Sequential Patches for Deepfake Detection cites Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
  • UCF: Uncovering Common Features for Generalizable Deepfake Detection cites Face X-Ray for More General Face Forgery Detection
  • UCF: Uncovering Common Features for Generalizable Deepfake Detection cites FaceForensics++: Learning to Detect Manipulated Facial Images
  • UCF: Uncovering Common Features for Generalizable Deepfake Detection cites OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training
  • Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics cites FaceForensics++: Learning to Detect Manipulated Facial Images
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers18

  1. UCF: Uncovering Common Features for Generalizable Deepfake DetectionZhiyuan Yan, Yong Zhang, Yanbo Fan, Baoyuan WuICCV 2023 · 264 citations
  2. Leveraging Real Talking Faces via Self-Supervision for Robust Forgery DetectionAlexandros Haliassos, Rodrigo Mira, Stavros Petridis, Maja PanticCVPR 2022 · 138 citations
  3. OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time TrainingLiang Chen, Yong Zhang, Yibing Song, Jue Wang et al.NeurIPS 2022 · 102 citations
  4. Delving into Sequential Patches for Deepfake DetectionJiazhi Guan, Hang Zhou, Zhibin Hong, Errui Ding et al.NeurIPS 2022 · 84 citations
  5. Exploring Frequency Adversarial Attacks for Face Forgery DetectionShuai Jia, Chao Ma, Taiping Yao, Bangjie Yin et al.CVPR 2022 · 78 citations

Builds on4

  1. FaceForensics++: Learning to Detect Manipulated Facial ImagesAndreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess et al.ICCV 2019 · 2,966 citations
  2. Face X-Ray for More General Face Forgery DetectionLingzhi Li, Jianmin Bao, Ting Zhang, Hao Yang et al.CVPR 2020
  3. DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery DetectionLiming Jiang, Ren Li, Wayne Wu, Chen Qian et al.CVPR 2020
  4. Celeb-DF: A Large-Scale Challenging Dataset for DeepFake ForensicsYuezun Li, Xin Yang, Pu Sun, Honggang Qi et al.CVPR 2020

Related papers

  1. Spatio-Temporal Catcher: A Self-Supervised Transformer for Deepfake Video DetectionMaosen Li, Xurong Li, Kun Yu, Cheng Deng et al.ACM MM 2023 · 9 citations
  2. One Detector to Rule Them All: Towards a General Deepfake Attack Detection FrameworkShahroz Tariq, Sangyup Lee, Simon S. WooWWW 2021 · 90 citations
  3. ID-Reveal: Identity-aware DeepFake Video DetectionDavide Cozzolino, Andreas Rössler, Justus Thies, Matthias Nießner et al.ICCV 2021 · 216 citations
  4. Beyond Spatial Frequency: Pixel-Wise Temporal Frequency-Based Deepfake Video DetectionTaehoon Kim, Jongwook Choi, Yonghyun Jeong, Haeun Noh et al.ICCV 2025 · 7 citations
  5. WildDeepfake: A Challenging Real-World Dataset for Deepfake DetectionBojia Zi, Minghao Chang, Jingjing Chen, Xingjun Ma et al.ACM MM 2020 · 443 citations
Dusk over the sea between two cliffs drawn in fine vertical lines