Research map / Label-efficient and robust learning / Recognition and long-tail
HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
Qing Wen, Haohao Li, Zhongjie Ba, Peng Cheng, Miao He, Li Lu, Kui Ren
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add amplification module (ablation) | HyperPotter · In-the-Wild | EER: 6.9 -> 5.72 | Improved |
| add amplification module (ablation) | HyperPotter · FoR | EER: 6.45 -> 3.89 | Improved |
| add amplification module (ablation) | HyperPotter · ASVspoof2021 LA | EER: 3.50 -> 3.94 | Hurt |
| add amplification module (ablation) | HyperPotter · ASVspoof5 | EER: 14.46 -> 16.04 | Hurt |
| add prototype banks (ablation) | HyperPotter · In-the-Wild | EER: 6.49 -> 5.72 | Improved |
| add prototype banks (ablation) | HyperPotter · ASVspoof2021 LA | EER: 2.80 -> 3.94 | Hurt |
| add prototype banks (ablation) | HyperPotter · FoR | EER: 4.59 -> 3.89 | Improved |
| add soft and slot alignment algorithms (ablation) | HyperPotter · ASVspoof5 | EER: 19.07 -> 16.04 | Improved |
| add soft alignment algorithm (ablation) | HyperPotter · In-the-Wild | EER: 7.45 -> 5.72 | Improved |
| add slot alignment algorithm (ablation) | HyperPotter · ASVspoof5 | EER: 19.90 -> 16.04 | Improved |
| add high-order hypergraph interactions to Wav2Vec2-AASIST | Wav2Vec2-AASIST · In-the-Wild | EER: 7.58 -> 5.72 | Improved |
| add high-order hypergraph interactions to Wav2Vec2-AASIST | Wav2Vec2-AASIST · ASVspoof2021 LA | EER: 2.48 -> 3.94 | Hurt |
Closest papers by meaning
- Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection (NeurIPS 2026 · similarity 0.87)
- I Can Hear You: Selective Robust Training for Deepfake Audio Detection (ICLR 2025 · similarity 0.86)
- Circumventing Shortcuts in Audio-visual Deepfake Detection Datasets with Unsupervised Learning (CVPR 2025 · similarity 0.85)
- Region-Based Optimization in Continual Learning for Audio Deepfake Detection (AAAI 2025 · similarity 0.84)
- AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection (CVPR 2024 · similarity 0.84)
- What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
