Scalable fragile watermarking for image authentication
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
Semi‐fragile watermarks are used to detect unauthorised changes to an image, whereas tolerating allowed changes such as compression. Most semi‐fragile algorithms that tolerate compression assume that because compression only removes the less visually significant data from an image, tampering with any data that would normally be removed by compression cannot affect a meaningful change to the image. Scalable compression allows a single compressed image to produce a variety of reduced resolution or reduced quality images, termed subimages, to suit the different display or bandwidth requirements of each user. However, highly scaled subimages remove a substantial fraction of the data in the original image, so the assumption used by most semi‐fragile algorithms breaks down, as tampering with this data allows meaningful changes to the image content. The authors propose a scalable fragile watermarking algorithm for authentication of scalable JPEG2000 compressed images. It tolerates the loss of large amounts of image data because of resolution or quality scaling, producing no false alarms. Yet, it also protects that data from tampering, detecting even minor manipulations other than scaling, and is secure against mark transfer and collage attacks. Experimental results demonstrate this for scaling down to 1/1024th the area of the original or to 1/100th the file size.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.008 |
| 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