ADA-FInfer: Inferring Face Representations From Adaptive Select Frames for High-Visual-Quality Deepfake Detection
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Interpretable deepfake detection is gaining attention for providing explainable, trustworthy results, avoiding the limitations of ‘black-box’ models. Current interpretable methods focus on visible artifacts in low-visual-quality deepfakes, but these artifacts become less apparent in high-visual-quality deepfakes generated by advanced models. With advancements in deep generative models, producing high-visual-quality deepfakes has become a strategy to evade detection. To address this, we propose <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula>, an adaptive frame selection and interpretable face representation inference method for detecting high-visual-quality deepfakes. <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula> adaptively selects frames by analyzing optical flow to reveal manipulations. We also introduce an adaptive attack method that manipulates specific frames, and our adaptive selection strategy shows resistance to such attacks. <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula> uses an encoder to learn face representations from source and target faces, applying a representation-prediction loss to maximize the distinction between real and fake videos. To provide further insights, we employ the joint entropy, mutual information, and conditional entropy analyses to explain the method's effectiveness. Extensive experiments and ablation studies demonstrate that <inline-formula><tex-math notation="LaTeX">${\sf ADA-FInfer}$</tex-math></inline-formula> achieves promising performance in detecting high-visual-quality deepfakes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it