- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3(+1)
Read review
Paper summary
The paper offers an attack enhancement method for Byzantine-robust federated learning, called GASP. The method starts with the assumption that the number of attackers is less than half of the clients and the attacker is omnicent, attacker knows all the client updates. The idea is to first find the crucial weights of the target model in each layer based on the loss and compare the updates with the reference set of generated anchor updates, and inject the attack residuals into the selected weights with a feasible scale controlled by a constant \lambda. The paper monitors the increase in the attack success rate and malicious admission rate of 5 different attacks against 9 different defenses and shows an increase in the attack success rate. The paper shows strengths in the aspects of experimental improvement, attack-agnostic methodology, and organized narration. However, it shows weaknesses in the aspects of the omniscient assumption and reference set-dependent methodology, model structure, and task simplicity.
Critical strengths
- The paper is well written and organized, with easy-to-follow sections that make the idea easy to grasp.
- Attack-agnostic enhancement makes the methodology generalizable and plug-and-play.
- The experiment clarity and improvement in the attack success rate by the GRASP.
Critical weaknesses
- The method uses simple tasks such as MNIST and CIFAR and performs on CNN-like architectures. These are still credible datasets and architectures, but I wonder how this strategy works in LLM/VLM based architectures like more focused on foundational models. This will raise the impact of the methodology.
- The credibility of the omniscient adversary is questionable; even though the authors provided a strategy that omits this, it still uses the compromised clients' pre-attack updates.
- The method could be highly dependent on the reference set, what if there is significant difference between this set and the clients' sets.
- As a comparison only, Pill (Guo et. al, 2026) is given as another enhancement method.
Questions for authors
- Does the method distinguish the honest non-IID update from a malicious update?
- The method is only attack oriented, but can this method be reversed to create a defense mechanism against the attacks or also improve the defense methods?
- For n=3 and m=1, we have q=1 which means there is no candidate model set to select majority. In this case, how does the GRASP behave?
- Why do you treat each layer with equal importance? Maybe some layers are more important than others.
6 comments
Response to Reviewer qxuk (2/4): W2 – Attacker-Local Variant; W3 – Dependence on the Reference Set
W2. The omniscient adversary and the attacker-local variant
The attacker-local variant still uses compromised clients' pre-attack updates.
We clarify what this requirement involves and what the variant demonstrates.
What a pre-attack update is. In round , a compromised client trains on its own data exactly as an honest client would, producing update . This is what it would have submitted before the adversary replaces it with the malicious one; it is neither an honest client's update nor a history collected before the attack begins. Any adversary that controls a client's data and training, as our threat model assumes, can compute it. For example, in cross-device FL an adversary can register or compromise several devices as Sybil clients (Fung et al., 2020) and run standard local training on each; the pre-attack update is simply the output of that training. Prior colluding attacks rely on the same information in their partial-knowledge settings: ALIE estimates coordinate statistics from the compromised workers' own updates (Baruch et al., 2019), and Fang et al. (2020) use the before-attack local models on compromised devices. An adversary without this information could not run local training.
Evidence. Appendix D, Table 15 evaluates GRASP with an attacker-local reference set built only from these updates. Over the 33 fully attacker-local settings (Sign Flipping, ALIE, and PoisonedFL × 11 defenses), the variant raises mean Attack Impact from 22.13 to 34.85 and exceeds Base in 28 of them; default omniscient GRASP reaches 34.89 on the same settings. Across all 66 settings (six attacks × eleven defenses), the variant averages 34.17, versus 34.83 for default GRASP and 24.35 for Base.
Scope. IPM, Min-Max, and Min-Sum still use honest updates through their base attacks, and the variant is evaluated on the MNIST configuration. We will add a concise parenthetical definition of pre-attack updates to the Threat Model in the revision.
W3. Dependence on the reference set
What happens if the reference set differs substantially from the clients' sets?
Where a mismatch can arise. is a set of current-round client updates, not a separate dataset: GRASP takes the anchor from and the radius from its pairwise distances. Under the default threat model, is exactly the set of honest updates, so no mismatch exists. A mismatch can arise only in the attacker-local variant, where consists of the compromised clients' pre-attack updates (W2).
How the variant sets the radius. The local set is smaller than the honest population (here 10 vs. 40 updates), so a percentile of its pairwise distances underestimates the honest radius . The variant rescales it by , where is Blom's approximation to the expected maximum of standard normals (Appendix D). The factor depends only on the set sizes ( here) and uses no honest update.
Existing evidence. All attacker-local experiments use Dirichlet , so the compromised clients' data already differ substantially from the honest clients'. The variant still matches default GRASP end to end (mean AI 34.17 vs. 34.83 over all 66 settings; Table 15).
New diagnostic. To test a stronger mismatch, we rebuilt the 10 local references from batches in which about 60% or 90% of the examples come from two classes, on normal MNIST training trajectories (5 seeds, 10 checkpoints each), with the honest updates, model state, and target update fixed. We measure (i) the signed error of the local radius relative to , which bounds the injection scale, and (ii) the distance from the local anchor to its nearest honest update, divided by , which shows whether the anchor lies within the honest population.
As the diagnostic table shows, with the original references () the uncalibrated radius error is −23.3% and the calibrated error is +6.9%. Under 90% two-class skew the uncalibrated error grows only to −29.1%, and the calibrated error is −1.1% (per seed −12.3% to +10.3%). The anchor distance is 0.36–0.42 with the original references and 0.36–0.40 under 90% skew. Most of the radius error therefore comes from the smaller set size, which calibration corrects; class skew adds about 6 points of error and barely moves the anchor.
Response to Reviewer qxuk (3/4): W4 – Pill as Baseline; Q1 – Honest Non-IID vs. Malicious; Q2 – Use as a Defense
W4. Pill as the only enhancement baseline
If we understand correctly, the concern is that GRASP is positioned against Pill as the only enhancement baseline. We clarify the comparison on two levels.
Scope of comparable methods. To the best of our knowledge, Pill (Guo et al., 2026) is the only directly comparable enhancement method we are aware of: an attack-agnostic wrapper that strengthens an arbitrary base attack by confining it to a parameter subspace. The other methods in our evaluation (Sign Flipping, ALIE, IPM, Min-Max, Min-Sum) are base attacks that GRASP wraps, not competing wrappers, so they are the objects of enhancement rather than baselines for it. Mimic serves as an attack reference in our ablations, not as a second enhancer.
Contribution over Pill. GRASP is not merely Pill with its heuristics swapped. Across all 198 FedSGD attack–defense settings (Tables 2, 4, and 5), GRASP exceeds Pill in 176/198 (88.9%) and the base attack in 180/198 (90.9%). The controlled ablations isolate the new components: the full method reaches an average Attack Impact of 42.69, versus 32.30 for the Pill-style scaling ablation. Please refer to our response to Reviewer NHGR (Weakness 4) for a detailed mapping of each design choice to the problem it addresses relative to Pill.
Q1. Does the method distinguish an honest non-IID update from a malicious update?
GRASP does not need to make this distinction, because its reference set is not sampled from the submitted updates.
How is constructed. is determined by the attacker's choice of reference set, not sampled at random from the pool of client updates. Under the default threat model, is, by construction, the set of honest updates in the current round, which the omniscient adversary observes (as in ALIE, Min-Max, and Min-Sum). In the attacker-local variant, consists of the compromised clients' own pre-attack updates, and the adversary knows which clients it controls. In both cases the attacker does not place malicious updates in , so no honest/malicious filtering step is required, and GRASP does not perform honest/malicious classification on the submitted updates.
Handling honest non-IID heterogeneity. Honest non-IID updates are therefore part of by construction under the default threat model. Their dispersion sets the radius (a percentile of the pairwise distances within ), so a more heterogeneous honest population yields a wider radius: as the Dirichlet concentration decreases from to , the normalized radius grows from 1.05 to 1.09 under Multi-Krum and from 1.27 to 1.36 under FLAME, while the honest distance distribution stays light-tailed (–; heterogeneity table). GRASP then selects the largest scale that keeps the crafted update within of at least references, so that together with the malicious submissions it reaches a geometric majority (Proposition 3).
Q2. Can the method be reversed into a defense, or used to improve defenses?
This is a valuable direction, and GRASP already offers a defender both a stress test and two concrete implications for defense design.
What GRASP already provides. As an attack-agnostic wrapper, GRASP is directly usable as a stress test for robust aggregation: it exposes where a given rule accepts localized, high-influence modifications that whole-update geometry does not flag.
A defense hypothesis it suggests. Our results point to two directions. First, geometric support does not imply task safety: GRASP stays within the majority-support region yet still causes damage, so proximity to many client updates is not sufficient evidence that an update is benign. Second, the attack concentrates in a small set of influential blocks, which suggests inspecting those blocks specifically rather than scoring the whole update, and combining block importance with a separate measure of in-block anomaly.
Why this is not a drop-in reversal. A high Shapley score marks a block as influential, not malicious, and honest non-IID updates may also concentrate in the same influential blocks. A defense built along these lines would therefore need validation for false positives on heterogeneous honest clients and for robustness to adaptive attackers; implementing and validating such a defense is left to future work.
Response to Reviewer qxuk (1/4): Summary of New Results; W1 – Foundation Models and Architectures
We thank the reviewer for the careful reading and for the constructive questions. We address the four weaknesses and four questions below. Revisions are marked in green; the new diagnostic in W3 is in the anonymous repository.
Throughout, Attack Impact (AI) denotes clean accuracy minus attacked accuracy, in percentage points (pp); a pre-attack update is the update a compromised client obtains by training on its own data in the current round, i.e., what it would submit before the adversary replaces it with the malicious update.
Summary of new results
W1. Foundation models and architectures
How does GRASP work on LLM/VLM-style architectures?
Scope first. We do not report end-to-end foundation-model experiments in this paper. Two settings are outside the current formulation and would need a different scoring objective: (i) protocols that aggregate the low-rank product rather than the LoRA factors, i.e., the product BA of the adapter ΔW=BA, and (ii) generative tasks, where "clean accuracy minus attacked accuracy" is not the natural target. What we can establish here is that the method is not tied to CNNs and maps to Transformer-style architectures without changing its formulation; we give that mapping below.
Evaluation scope so far. Our evaluation follows the setting in which the base attacks and defenses we wrap were proposed and benchmarked, from LeNet on MNIST to ResNet-18 on CIFAR-10 (11.17M parameters, 972 blocks). Extending GRASP to federated adaptation of foundation models is a natural next step.
GRASP does not depend on the architecture. It requires only (i) a block partition of the trainable parameters, (ii) per-example gradients on a small attacker-held scoring panel, and (iii) Euclidean geometry over flattened updates. Each has a direct counterpart in Transformers:
An end-to-end evaluation on foundation models is a natural next step; the two settings noted above each require a dedicated formulation rather than a re-parameterization of the current one, which we leave to future work.