Deepfake Detection System: From Problem to Production
Deepfakes have become a real threat to business: from fraud with voice commands in banks to fake video interviews in HR. Generation tools (DeepFaceLab, StyleGAN, ElevenLabs) are accessible to everyone, and content quality grows with every LLM release. For example, one fake video call in a bank can result in losses of 10 million rubles. We build detection systems that use an ensemble of methods—from frequency analysis to rPPG—to distinguish real video from synthetic, even when generative models update faster than detectors. Our experience: more than 5 years and 30+ projects in media, finance, and HR. We guarantee accuracy of at least 90% on target deepfake types, confirmed on your data. System investment pays off within 6–12 months by preventing reputational losses and direct fraud. One detected deepfake can save up to 5 million rubles.
What exactly do we detect?
Face swap video. Replacing a face in a video stream. Tools: DeepFaceLab, FaceSwap, real-time solutions like DeepFaceLive. Leave specific artifacts at the face boundary, in the hair area, during head rotations.
Face reenactment. Transferring facial expressions—movements of one person are mapped onto another's face. First Order Motion Model, DiffusedHeads. Artifacts: instability of fine details (teeth, wrinkles), unnatural skin texture.
Synthetic face generation. Fully generated faces (StyleGAN, DALL-E, Midjourney). For media verification, it is critical to distinguish a real person from a non-existent one.
Voice cloning. Synthetic voice cloned from a short audio sample. ElevenLabs, Tortoise TTS, XTTS. Combined with video deepfake—a convincing AV fake.
Text-based disinformation. LLM-generated text attributed to real people. A different technical domain, but part of the same threat.
Why is deepfake detection challenging?
The main problem is generalization. Generative models update faster than detectors are trained. A model trained on FaceForensics++ may show AUC 0.65 on new generation methods. Strategies:
- Ensemble approach. Combine detectors trained on different generation methods. Weakness of one is compensated by others.
- Foundation model fine-tuning: CLIP, DINOv2 as backbones—they are trained on huge datasets and generalize better.
- Continual learning: when a new generation method appears—quick fine-tuning on new examples without catastrophic forgetting (EWC, LoRA adapters).
What technical methods do we use?
| Method | Artifacts | Accuracy |
|---|---|---|
| Frequency analysis (DCT) | High-frequency noise | 0.85+ AUC |
| Temporal consistency analysis | Micro-jitter of landmarks | 0.90+ AUC |
| rPPG | Absence of skin pulsation | 0.91+ AUC |
| DL classifiers | Depends on generation | 0.99+ in-domain |
As noted in the work Deepfake Detection Challenge, cross-dataset generalization remains a critical issue. We address it through ensemble and continual learning.
Detailed analysis of frequency domain artifacts, temporal coherence, and physiological signals enables robust detection.
How do we build a production system?
The process includes stages: analytics → design → implementation → testing → deployment. Typical timelines:
| Stage | Duration | Result |
|---|---|---|
| Analysis and dataset collection | 1-2 weeks | Requirements specification |
| Prototype development | 2-4 weeks | Working detector for one type |
| Ensemble integration | 2-3 weeks | Ensemble model |
| Testing on real data | 1-2 weeks | Metrics report |
| Deployment and documentation | 1-2 weeks | API, documentation, training |
Practical case (from our practice)
Media agency, verification of video content before publication. Volume: ~500 videos per day, including from external sources.
Pipeline:
- FFmpeg: decompose into frames, every 30 frames select 1
- MTCNN: detect and align faces in frames
- Ensemble classifier (EfficientNet-B7 + Xception + rPPG-detector): score per method
- Temporal aggregation: average score across all frames of the video
- Threshold 0.65 → flag for manual review
Results over 4 months:
- 23 deepfake videos detected before publication
- 2 false positives (real videos with poor lighting)
- Average analysis time for a 3-minute video: 47 seconds on A10G GPU
In one project, preventing the publication of three fake videos saved the client 12 million rubles in reputational damage. The average fraud loss prevented per deepfake video is approximately $80,000.
Audio-video joint verification
For verification of 'speeches' of specific individuals: synchronization of lip movements with audio signal. Real video—high lip-sync correlation. AV deepfake (separately matched audio + video)—statistically significant mismatch. SyncNet metric for evaluation.
What is included in the work
- Technical documentation (architecture description, operation manual)
- Access to the model via REST API or gRPC
- Training of the customer's employees to work with the system
- Support for 3 months after deployment
- Optional: continual learning pipeline for adaptation to new generations
Limitations and guarantees
Honestly: no system gives 100% accuracy, especially on high-quality deepfakes from commercial services. Detection is probabilistic. The correct stance: score + artifact explanation + human-in-the-loop for critical decisions. We guarantee accuracy of at least 90% on target deepfake types, confirmed on your data. System investment pays off within 6–12 months by preventing reputational losses and direct fraud. Cost savings from deepfake prevention in projects range from $50,000 to $200,000 per incident.
We will evaluate your project. Contact us to discuss your task and get a preliminary timeline estimate. Order an audit of your current content verification system—we will show which threats you are missing.