AuthAttLyzer: A Robust defensive distillation-based Authorship Attribution framework
Bibliographic record
Abstract
Source Code Authorship Attribution (SCAA) is the technique to find the real author of source code in a corpus. Though it is a privacy threat to open-source programmers, it has shown to be significantly helpful in developing forensic-based applications such as ghostwriting detection, copyright dispute settlements, catching authors of malicious applications using source code, and other code analysis applications. Recent advances in SCAA techniques have performed exceptionally well on varied datasets. However, recent works on gradient-based attacks and universal perturbations can adversarially modify source code to reduce the accuracy of state-of-the-art classification techniques based on deep neural networks to as low as 10%. In this paper, we derive inspiration from recent advances in cyber-security and propose using the concept of defensive distillation to create a new architecture for source code authorship attribution with increased robustness against such adversarial attacks (reduce sent size). We empirically show that our approach, defensive distillation, and varied feature selection reduce miss-classification on perturbed source code files for Google code Jam and GitHub database while maintaining a 95% accuracy on legitimate source code files.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".