On the feasibility of inference attacks by third-party extensions to social network systems
Bibliographic record
Abstract
Social Network Systems (SNSs) providers allow third-party extensions to access users' information through an Application Programming Interface (API). Once an extension has been authorized by a user to access data in a user's profile, there is no more control on how that extension uses the data. This raises serious concerns about user privacy because a malicious extension may infer some private information based on the legitimately accessible information. This information leakage is called an inference attack. In addition, inference attacks are not only a privacy violation, they could also be used as the building blocks for more dangerous security attacks, such as identity theft. In this work, we conduct a comprehensive empirical study to assess the feasibility and accuracy of inference attacks that are launched from the extension API of SNSs. We also discuss an attack scenario in which inference attacks are employed as building blocks. The significance of this work is in thoroughly discussing how inference attacks could happen in practice via the extension API of SNSs, and highlighting the clear and present danger of even the naively crafted inference attacks.
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 | 0.056 | 0.327 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.004 | 0.010 |
| Scholarly communication | 0.006 | 0.023 |
| Open science | 0.003 | 0.007 |
| Research integrity | 0.007 | 0.009 |
| Insufficient payload (model declined to judge) | 0.003 | 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".