- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper introduces OTPA, an untargeted model-poisoning attack for federated learning. Using local data and the broadcast model, it aligns a stored poisoned model with a freshly trained clean anchor through entropic optimal transport, then interpolates the two for submission. On CIFAR-10, OTPA reduces global accuracy from 66.69% to 39.41%, with a median update distance of 5.47 compared with 55.00 for unaligned interpolation. It outperforms the evaluated attack baselines under six robust aggregators, while FoolsGold and FLAME neutralize it in the reported settings.
Critical strengths
-
The proposed attack produces a substantial impact-distance tradeoff. On CIFAR-10, OTPA reduces global accuracy from 66.69% to 39.41%, while its median update distance is 5.47 compared with 55.00 for matched unaligned interpolation. Across the three primary vision datasets, it reduces median distance by 70-90% relative to Linear while remaining within 2.5 accuracy points of its impact. Matching the source, anchor, interpolation weight, and schedule makes this a useful comparison of the complete transport operation.
-
The evaluation includes actual robust aggregation mechanisms. OTPA leaves approximately 43-46% CIFAR-10 accuracy under Krum, Multi-Krum, trimmed mean, coordinatewise median, RFA, and FLTrust, lower than every evaluated baseline in those columns. These results provide more direct evidence of attack effectiveness than update distance alone.
-
The construction is evaluated across multiple architectures, heterogeneous partitions, partial participation, and a language task. The paper distinguishes attacker-local baselines from those receiving honest-update information. It also reports effective countermeasures: FoolsGold and FLAME neutralize OTPA in the tested runs, and DnC substantially reduces its impact.
Critical weaknesses
-
The incremental novelty over the closest prior attack is not sufficiently established. FL-MMR already uses optimal transport to align poisoned and benign models for federated poisoning, and the authors acknowledge it in Table 6. OTPA's persistent source, refreshed anchor, dense interpolation, and architecture coverage may provide useful differences, but the paper does not compare against FL-MMR experimentally or isolate the benefit of those differences. Existing transformer OT fusion also already addresses attention, normalization, and residual routing. The paper should identify which part of the attack is new and demonstrate its value relative to the closest predecessor under comparable information and resource assumptions.
-
The results establish the value of the complete transport operation, but do not establish the attack benefit of learned feature correspondence beyond contraction and mixing. Appendix E.1 shows that a uniform map reduces source-anchor distance from 62.85 to 10.10, compared with 8.23 for solved OT. The authors acknowledge that contraction accounts for most of the reduction. However, these controls are evaluated only for a round-100 construction, without complete training trajectories or defended accuracy. This leaves open whether simpler contraction can reproduce the main attack results. It does not invalidate OTPA's observed effectiveness, but weakens the explanation of why its central design is needed.
-
The statistical support for the main defense comparison is incomplete. Table 2 reports Student-t confidence intervals without specifying the replicate count and seed protocol for each condition. Table 4 provides no uncertainty or clean no-attack rows for its seven mechanisms, while the alignment ablation and explicit-filter evaluations are single runs. The reported margins under six aggregators are substantial, but repeated runs and defense-specific clean controls are needed to assess their stability and quantify the accuracy loss attributable to each attack.
-
A smaller update distance does not necessarily imply greater stealthiness. Malicious updates influence the reference center, and comparisons with a separate clean run do not show whether OTPA resembles honest updates during the attack. The authors should compare malicious and honest updates within the same attacked run; the reported failures against FoolsGold and FLAME further limit claims of general defense evasion.
-
The defense evaluation omits recent relevant methods, including FoundationFL (NDSS 2025), LASA (WACV 2025), and FedREDefense (ICML 2024). Comparisons under compatible assumptions would clarify whether OTPA’s effectiveness extends to these defenses, particularly given its limited success against DnC, FoolsGold, and FLAME.
Questions for authors
-
What is the main technical advance over FL-MMR, and can the authors compare the two under matched attacker information, compromise rates, and resource budgets?
-
Do uniform-map and contraction-matched randomized-map controls retain poisoning impact and evade the same aggregators over complete training runs? This would directly test whether learned correspondence is necessary for the reported advantage.
-
How many independent runs support each confidence interval, and can the authors add uncertainty and defense-specific clean controls to Table 4?
-
Does the geometric and defended-accuracy advantage persist when evaluated against honest-client geometry in the same run and at lower compromise rates?
-
Can the authors evaluate representative recent defenses such as FoundationFL, LASA, and FedREDefense, with their required assumptions and defense-specific clean accuracy clearly reported? If a method is incompatible with the threat model or protocol, please explain the incompatibility.