Is AI Interpretability Safe: the Relationship between Interpretability and Security of Machine Learning Models
Bibliographic record
Abstract
With the growing application of interpretable artificial intelligence (AI) models, increasing attention is being paid to issues of trust and security across all types of data. In this work, we focus on the task of graph node classification, highlighting it as one of the most challenging. To the best of our knowledge, this is the first study to comprehensively explore the relationship between interpretability and robustness. Our experiments are conducted on datasets of citation and purchase graphs. We propose methodologies for constructing black-box attacks on graph models based on interpretation results and demonstrate how adding protection impacts the interpretability of AI models.
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 | 0.037 | 0.286 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.016 |
| Scholarly communication | 0.010 | 0.021 |
| Open science | 0.003 | 0.007 |
| Research integrity | 0.005 | 0.011 |
| Insufficient payload (model declined to judge) | 0.004 | 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".