Exploring Comparative Visual Approaches for Understanding Model Trade-offs in Adversarial Machine Learning
Bibliographic record
Abstract
Despite the effectiveness of adversarial training (AT) in enhancing model robustness, it suffers from the accuracy-robustness trade-off and the “robust fairness” problem. To strategize effectively, practitioners have the need to explore and compare model performance in both standard and adversarial settings concurrently. This work presents a design study with 11 experts to explore effective comparative visual techniques for multi-level trade-off analysis. We first collaborated with five adversarial machine learning (AML) experts in an iterative design process, based on which we developed a visual analytics design probe, VATRA, that employs an augmented hybrid comparative design to support concurrent accuracy and robustness evaluations for assessing model trade-offs. Further, we conducted user studies with six domain experts and derived two in-depth use cases of VATRA, providing empirical knowledge about how ML practitioners can leverage comparative visualizations for AML trade-off analysis.
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 | 0.026 | 0.072 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 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".