- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates persistent poisoning attacks in federated load forecasting under non-IID data distributions. To mitigate the two proposed poisoning attacks, the paper proposes FedRASR, a server-side defense that constructs region-calibrated client update trajectories, extracts temporal frequency characteristics using FFT, estimates client risk, and adaptively reweights model updates during aggregation. The results show that FedRASR achieves lower forecasting errors than the evaluated robust aggregation baselines.
Critical strengths
-
The paper addresses a meaningful problem in heterogeneous federated learning.
-
The evaluation includes multiple regional datasets and ablations.
Critical weaknesses
-
The evaluated attacks may exhibit temporal signatures that are particularly favorable to the proposed frequency-domain detector. The authors should evaluate additional poisoning schedules, such as randomized and adaptive attacks, to establish whether the proposed method captures general persistent malicious behavior.
-
FedRASR relies on regional medians and MAD-based thresholds to separate benign heterogeneity from malicious behavior. However, the threat model specifies only a global malicious-client fraction and does not impose a corresponding bound on the malicious fraction within each region. Attackers could therefore concentrate compromised clients in particular regions and potentially bias both the reference centers and risk thresholds.
-
Why the results in Tables S7–S8 show substantial regional variation?
-
The paper discusses FreqFed, FedRDF, and FLDetector but does not include them in the experimental evaluation. The compared methods are relatively outdated.
Questions for authors
Please check weaknesses.
3 comments
Response by Authors (Part 2)
W3: Regional Variation
Thanks for pointing it out. It is the regional variation that reflects the heterogeneous (non-i.i.d.) data among clients in different regions. This is actually one of our challenges and motivations in Attack and Defense in Federated Load Forecasting. To address this, we develop regional calibration to mitigate the impact of benign regional heterogeneity on poisoning detection. On the other hand, under clean training, the performance differences are already observed ( clean FedAvg in Table 3). To further demonstrate the effectiveness of FedRASR across different regions, we conduct experiments and expand the testing clients from 10 to 300 per region (this will further increase the heterogeneity). As shown in Table 3, FedRASR consistently outperforms FedAvg across all four regions under both attacks, achieving 7.7%–19.1% RMSE reductions under Hist-Residual and 4.8%–19.4% under Profile-LIE. These results demonstrate that FedRASR's improvements are not limited to a particular region.
Table 3. Regional RMSE on the expanded held-out test cohort.
| Region | Clean FedAvg | Hist-Residual FedAvg | Hist-Residual FedRASR | Profile-LIE FedAvg | Profile-LIE FedRASR |
|---|---|---|---|---|---|
| Portugal | 0.1118 | 0.1579 | 0.1277 | 0.1590 | 0.1281 |
| Ausgrid | 0.0740 | 0.0833 | 0.0762 | 0.0794 | 0.0752 |
| London | 0.0803 | 0.0892 | 0.0823 | 0.0855 | 0.0814 |
| Swiss | 0.0927 | 0.1055 | 0.0960 | 0.1017 | 0.0951 |
W4: More baselines.
Thanks for pointing it out. We have added three baselines (FreqFed, FedRDF, and FLDetector) as requested. The results are in the table below.
| Method | RMSE Clean ↓ | RMSE Hist-Residual ↓ | RMSE Profile-LIE ↓ | MAE Clean ↓ | MAE Hist-Residual ↓ | MAE Profile-LIE ↓ |
|---|---|---|---|---|---|---|
| FedRASR (ours) | 0.0897 ± 0.0022 | 0.0955 ± 0.0022 | 0.0950 ± 0.0020 | 0.0628 ± 0.0017 | 0.0719 ± 0.0029 | 0.0703 ± 0.0024 |
| FreqFed | 0.0989 ± 0.0078 | 0.1044 ± 0.0099 | 0.0956 ± 0.0043 | 0.0696 ± 0.0063 | 0.0769 ± 0.0119 | 0.0760 ± 0.0038 |
| FLDetector | 0.0928 ± 0.0029 | 0.1039 ± 0.0032 | 0.1063 ± 0.0055 | 0.0646 ± 0.0026 | 0.0779 ± 0.0032 | 0.0798 ± 0.0052 |
| FedRDF | 0.0931 ± 0.0029 | 0.1036 ± 0.0035 | 0.1056 ± 0.0047 | 0.0651 ± 0.0023 | 0.0776 ± 0.0034 | 0.0791 ± 0.0046 |
Dear Reviewer:
Thank you very much for your constructive comments. We hope that our responses have addressed your concerns. Please feel free to let us know if any further clarification is needed.
Best regards,
The authors
Response by Authors (Part 1)
We are grateful to the reviewer for recognizing the importance of the problem and the evaluation across regional datasets. We will clarify the attack schedules, reference conditions, regional variation, and baseline comparisons separately below.
W1: Robustness beyond alternating schedules
Thanks for pointing it out. We agree that evaluating only alternating attacks limits the generalizability of FedRASR. Therefore, we additionally evaluate constant-sign and randomized-sign attacks, and compare zero-filled and observed-only trajectories. As shown in Table 1, zero-filled FedRASR achieves the lowest mean RMSE and MAE among the three compared methods across all six settings, demonstrating that its advantage is not restricted to alternating attacks.
Table 1. Attack schedule and trajectory comparisons.
W2: Concentrated Contamination
We thank the reviewer for raising this concern. Our threat model is based on a fixed malicious-client pool randomly sampled from the global population, with a 30% malicious-client ratio (to satisfy the minority assumption for adversaries), following the commonly adopted benign-majority setting in robust federated learning [1, 2]. On the other hand, only a subset of clients participate in the training (normally no more than 20% of all clients). The probability that malicious clients dominate a particular region's participating clients is very low. Thus, the scenario (attackers dominate a specific region) is unlikely under our considered threat model and represents a more extreme adversarial setting.
Nevertheless, to directly address this concern, we further evaluate a challenging scenario where 49% of clients in a specific region (Portugal) are malicious (Must < 50% to follow the protocol). This setting substantially increases regional adversarial concentration compared with our original random-compromise setting. In the tables below, FedRASR still works and achieves the lowest mean RMSE and MAE among the three compared methods and these results demonstrate FedRASR's robustness under concentrated regional poisoning.
Hist-Residual
Profile-LIE
[1] Chulin Xie, Keli Huang, Pin-Yu Chen, and Bo Li. Dba: Distributed backdoor attacks against federated learning. In International conference on learning representations. 2019
[2] Dong Yin, Yudong Chen, Ramchandran Kannan, and Peter Bartlett. Byzantine-robust distributed learning: Towards optimal statistical rates. In International conference on machine learning. 2018