Digital watermarks for videos based on a locality-sensitive hashing algorithm
Bibliographic record
Abstract
Abstract Sensitive information in images is leaked during attacks, resulting in the malicious acquisition of personal privacy. To improve the robustness of attacking defence for video images, a digital watermarking algorithm based on locality-sensitive hashing (LSH) is designed. The video signal was decomposed using a one-dimensional wavelet transform. According to the Yeung Mintzer (Y-M) algorithm, a marker watermark W1 was embedded in the low-frequency subband to identify image tampering. The data string of hash function values and the exclusive OR (XOR) result of identification watermark W2 were embedded into the HH high-frequency subband, which was used to identify and counter the pseudo-authentication attacks such as collage and Vector Quantization(VQ). The singular value decomposition (SVD) algorithm was used to decompose the hash-mapped watermark and adaptively adjust the embedding strength of the watermark. The position-sensitive hash algorithm proposed has good invisibility for embedding digital watermarks into images, with an average accuracy of approximately 97% for feature matching of digital images. The PSNR value of the image embedded with the watermark is approximately 49 dB. At the 50th minute of the experiment, the regulatory factor value of the research method was 0.3. Under different attack modes, the correlation coefficient between the watermark extracted by this method and the original watermark image is greater than 0.85. Due to the low compression quality of JPGE, the correlation coefficient between the watermark and the initial watermark is greater than 0.6, and its error rate is less than 0.10bit.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".