Eyes on Federated Recommendation: Targeted Poisoning With Competition and Its Mitigation
Bibliographic record
Abstract
Federated recommendation (FR) addresses privacy concerns in recommender systems by training a global model without requiring raw user data to leave individual devices. A server, known as the aggregator, integrates users’ local gradients and updates the global model parameters. However, FR is vulnerable to attacks where malicious users manipulate these updates, known as model poisoning attacks. In this work, we propose a new targeted attack called <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">StairClimbing</monospace> to promote specific items through model poisoning, and a new defence mechanism <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CrossEU. StairClimbing</monospace> adopts a new strategy resembling stair climbing to enable target items to beat competitive items and increase their popularity level by level. Compared to prior attacks, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">StairClimbing</monospace> guarantees balanced effectiveness, efficiency and stealthiness simultaneously. Our defence mechanism <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CrossEU</monospace> leverages two patterns regarding the lists of items updated by benign users between iterative epochs. Extensive experiments on six real-world datasets demonstrate <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">StairClimbing</monospace>’s superiority across all three desirable attack properties, even with a small proportion of malicious users (1%). In addition, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CrossEU</monospace> effectively delays the impact of all tested attacks and even eliminates their damage entirely.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".