Bibliographic record
Abstract
CAPTCHAs are automated Turing tests used to determine if the end-user is human and not an automated program. Users are asked to read and answer Visual CAPTCHAs, which often appear as bitmaps of text characters, in order to gain access to a low-cost resource such as webmail or a blog. CAPTCHAs are generated by software and the structure of a CAPTCHA gives hints to its implementation. Thus due to these properties of image processing and image composition, the process that creates CAPTCHAs can often be reverse engineered. Once the implementation strategy of a family of CAPTCHAs has been reverse engineered the CAPTCHA instances may be solved automatically by leveraging weaknesses in the creation process or by comparing a CAPTCHA's output against itself. In this paper, we present a case study where we reverse engineer and solve real-world CAPTCHAs using simple image processing techniques such as bitmap comparison, thresholding, fill-flood segmentation, dilation, and erosion. We present black-box and white-box methodologies for reverse engineering and solving CAPTCHAs. As well we provide an open source toolkit for solving CAPTCHAs that we have used with a success rates of 99, 95, 61, 30%, and 27% on hundreds of CAPTCHAs from five real-world examples.
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 | 0.003 | 0.032 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
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".