Robust Black-box Watermarking for Deep Neural Network using Inverse Document Frequency
Bibliographic record
Abstract
Recently, Deep Neural Networks (DNNs), presented exceptional achievement in implementing human-level capabilities for various predicaments, such as Natural Language Processing (NLP), voice recognition, and image processing, etc. Training these models is expensive in terms of computational power and the existence of enough labelled data. Thus, ML-based models such as DNNs establish genuine business value and intellectual property (IP) for their owners. Therefore the trained models need to be protected from any adversary attacks such as illegal redistribution, reproducing, and derivation. Watermarking can be considered as an effective technique for securing a DNN model. However, so far, most of the watermarking algorithms focus on watermarking the DNN by adding noise to an image. To this end, we propose a framework for watermarking a DNN model designed for textual domain. The watermark generation scheme provides a secure watermarking method by combining Term Frequency (TF) and Inverse Document Frequency (IDF) of a particular word. The proposed embedding procedure takes place in the model's training stage, which makes the watermark verification stage straightforward by sending the watermarked document to the trained model. The experimental results show that watermarked models have the same accuracy as the original one, and the proposed framework accurately verifies the ownership of all surrogate models without impairing the performance. The proposed algorithm is robust against well-known attacks such as parameter pruning and brute force attack.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".