Defenses to Membership Inference Attacks: A Survey
Bibliographic record
Abstract
Machine learning (ML) has gained widespread adoption in a variety of fields, including computer vision and natural language processing. However, ML models are vulnerable to membership inference attacks (MIAs), which can infer whether access data was used in training a target model, thus compromising the privacy of training data. This has led researchers to focus on protecting the privacy of ML. To date, although there have been extensive efforts to defend against MIAs, we still lack a comprehensive understanding of the progress made in this area, which can often impede our ability to design the most effective defense strategies. In this article, we aim to fill this critical knowledge gap by providing a systematic analysis of membership inference defense. Specifically, we classify and summarize the existing membership inference defense schemes, focusing on optimization phase and objective, basic intuition, and key technology, and we discuss possible research directions of membership inference defense in the future.
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 | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.004 | 0.011 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.004 | 0.005 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".