- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates security vulnerabilities in federated unlearning (FU), focusing on how malicious clients can manipulate model predictions through coordinated training-data modifications and unlearning requests. The authors propose BURST, an attack framework that constructs two complementary sets from public auxiliary data: a target-support set that reinforces correct predictions and an interference set that promotes competing-class predictions. During federated training, both sets are incorporated into malicious clients’ local datasets. During unlearning, the attacker removes the support set and strengthens the interference set through optimized perturbations, aiming to turn previously correct predictions into misclassifications. Experiments on MNIST and CIFAR-10 demonstrate the effectiveness of BURST against existing attacks, including BadFU and FedMUA. On CIFAR-10, BURST achieves a 91.43% attack success rate while reducing global accuracy by 5.66 percentage points.
Critical strengths
S1. The paper addresses an important vulnerability in federated unlearning, highlighting that unlearning requests and subsequent model reconstruction can introduce security risks beyond conventional training-time attacks.
S2. The combination of target-support removal and interference enhancement provides a coherent mechanism for manipulating predictions specifically during the unlearning stage.
S3. BURST achieves substantially higher attack success rates than the evaluated baselines, particularly on CIFAR-10 (91.43% compared with 60.00% for FedMUA).
S4. BURST avoids the expensive Hessian-based influence estimation required by FedMUA and demonstrates substantially lower attack-construction overhead.
Critical weaknesses
W1. The attack assumes access to the target sample and its ground-truth label, a suitable public auxiliary dataset, and the ability to manipulate client-side reconstruction or recalibration. These assumptions may limit its applicability to practical FU systems.
W2. Although the paper identifies security vulnerabilities, it does not experimentally investigate whether existing malicious-update detection, data validation, or robust aggregation mechanisms can mitigate BURST.
W3. The reported runtime comparison excludes surrogate-model training, federated training, and unlearning. Consequently, the results do not establish the end-to-end computational advantage of BURST.
Questions for authors
Q1. Section 3.1 defines an unlearning request as r=(F,q), where F is the forget set and q contains protocol-specific information. However, Algorithm 1 constructs the malicious request as \tilde r=(S,\tilde I). It is unclear how the enhanced interference set is incorporated into the standard FU interface and whether the assumed FU methods permit this operation. This distinction is important because the attack relies on manipulating both removal and reconstruction.
Q2. The methodology constructs attack sets before federated training, whereas Section C.4 describes selecting target samples based on their correct classification by the pre-unlearning model. The paper should clarify whether targets are selected using a separately trained reference model or whether attack construction and target filtering are performed iteratively. This matters because target selection could introduce evaluation bias.
Q3. The paper requires p_i\leq k_i, but this does not guarantee that the selected competing class contains at least p_i samples within the retrieved neighborhood. The authors should clarify how the algorithm handles cases where fewer than p_i samples belong to the selected class.
Q4. The analysis defines the target margin relative to the strongest competing class before unlearning. However, this competing class may change after unlearning. Consequently, the statement that a nonpositive margin necessarily characterizes post-unlearning misclassification is valid as a sufficient condition, but not generally as an equivalent characterization. The distinction should be clarified.
Q5. The paper states that attack-specific budgets are matched across methods, but Appendix C.3 qualifies this as being done “whenever possible.” The authors should explicitly report the actual sample budgets for each baseline to establish the fairness of the comparisons.
Q6. Table 2 reports only 1.041 seconds for BURST’s attack construction, while the methodology requires surrogate-model training and feature-space retrieval. It is unclear whether these operations are included in the reported runtime. Additionally, Appendix A models perturbation optimization using a second-order operation cost, although the proposed optimization does not explicitly require second-order derivatives. These aspects should be clarified.
Q7. FedMUA achieves a substantially higher confidence gap than BURST on CIFAR-10 (86.38 versus 30.74 percentage points), despite having a lower attack success rate. The paper emphasizes BURST’s effectiveness but does not sufficiently discuss this trade-off between attack success frequency and misclassification confidence.
Code README.md should be written English rather than Chinese.
10 comments
Response to Reviewer 5x8V (2/5): W3 & Q1 - Runtime Scope and FU Interface
Critical Weakness 3: Scope of the Runtime Comparison
Table 2 reports attack-construction time with a prepared surrogate model. The efficiency comparison therefore concerns the attack-construction stage, excluding surrogate-model training, federated training, and unlearning execution.
Surrogate preparation and reuse. The surrogate model is reusable across targets within the same task and does not require retraining for each target. A compatible pretrained model can also serve as the surrogate. We therefore distinguish surrogate preparation from per-target attack construction when reporting computational costs.
Shared training and unlearning protocols. All compared attack methods use the same federated training and unlearning protocols and configurations. Neither BURST nor the compared baselines modifies the underlying federated training or unlearning protocol; their attack-specific operations concern sample construction and the use of these samples within the prescribed workflow. Table 2 focuses on the computational overhead of attack construction within this shared experimental framework.
In the revised manuscript, we explicitly define the timing scope in Section 5.4 and Appendix C.6.
Q1: Unlearning Requests and Client-Side Interference Enhancement
The enhanced interference set is not part of the unlearning request submitted to the server. The request is , while interference enhancement is performed locally by the interference-holding client during calibration. These are separate operations within the stated threat model.
In the revised manuscript, we align Algorithm 1 with the interface defined in Section 3.1 as follows:
1. Request representation. We retain the definition in Section 3.1 and replace in the request-construction step of Algorithm 1 with . Here, , and contains only protocol-required information. The enhanced interference set is not included in the request.
2. Algorithm execution. We expand the original lines 10–11 into the following steps:
- Submit the unlearning request .
- When the FU procedure invokes local calibration, the client holding the support set uses its remaining data after removing . The client holding the interference set locally replaces with its label-preserving enhanced version and computes updates through the prescribed local training procedure.
- The server performs calibration and aggregation based on the request and the returned client updates, producing .
3. Corresponding descriptions in the main text and appendix. In Section 4.3 and Appendix B, we describe the two operations as follows:
The unlearning request identifies as the forget set; the enhanced interference set is used locally by its holder during calibration, and the server receives only the resulting model updates.
In our sample-level adaptation of FedEraser, the interference-holding client continues to participate in calibration and performs these operations through its control over local data. This requires neither additional server-side request fields nor adversarial capabilities beyond the stated threat model.
Response to Reviewer 5x8V (3/5): Q2 & Q3 - Target Screening and Sample Availability
Q2: Target Screening and Evaluation Eligibility
Targets are screened before attack construction using a separately trained and frozen surrogate model, and the subsequent eligibility check does not trigger target replacement or attack-set reconstruction. Therefore, this procedure does not introduce selection bias arising from iterative target filtering driven by the pre-unlearning check.
Target screening before attack construction. Specifically, we first screen candidate targets using the surrogate model and retain those it classifies correctly. We then construct the support and interference sets for the selected targets and perform federated training.
Eligibility check after federated training. After federated training, we check whether the resulting pre-unlearning global model correctly classifies each target. This check establishes eligibility for evaluating a successful flip from a correct prediction before unlearning to an incorrect prediction afterward. It is distinct from the surrogate-based screening performed before attack construction. The eligibility-check outcome does not trigger a return to attack construction, target replacement, or reconstruction of the attack sets.
In the revised manuscript, we revise the opening paragraph of Section C.4 to state this sequence explicitly and distinguish surrogate-based target screening before attack construction from the eligibility check after federated training.
Q3: Ensuring Sufficient Samples in the Selected Competing Class
We ensure sufficient samples in the selected competing class by enforcing a stronger input constraint before retrieval. Parameter configurations that violate this constraint are rejected before attack construction.
Sufficient input constraint. Specifically, we require
$ p_i \leq \left\lceil \frac{k_i}{C-1} \right\rceil, \qquad k_i \leq |\mathcal C_{\mathrm{int}}|, $
where is the total number of classes and is the candidate pool after excluding the target class. Here, denotes the number of distinct interference images selected, before any repetition used to form training records.
The retrieved neighbors belong to at most competing classes. By the pigeonhole principle, the most frequent class contains at least samples. The strengthened constraint therefore guarantees that the selected class contains at least samples.
Experimental configurations. All reported experiments satisfy this condition. Both datasets have classes:
| Dataset | Retrieved neighbors | Selected images | Guaranteed minimum count in the selected class |
|---|---|---|---|
| MNIST | 50 | 5 | 6 |
| CIFAR-10 | 1,000 | 60 | 112 |
In the revised manuscript, we explicitly state this sufficient condition in Algorithm 1 and specify that the candidate pool excludes the target class before retrieval. We validate these constraints before retrieval to ensure that the subsequent class-specific selection is feasible.
Response to Reviewer 5x8V (1/5): W1 & W2 - Threat Model and Defenses
Critical Weakness 1: Practical Applicability of the Threat Model
Access to the target sample and its ground-truth label. These assumptions correspond to targeted attack scenarios in which routine collaboration gives two participating clients access to the same labeled target. In hospital referrals, an authorized transfer of a dermoscopic image and its pathology-confirmed diagnosis allows both the referring and receiving hospitals to hold the same target and label. An attacker controlling participating nodes aims to compromise the shared model’s automated assessment of that case.
In collaborative phishing detection, security organizations can share the same webpage screenshot and its verified phishing label through joint investigations and threat-intelligence exchange. MISP supports such cross-organizational information sharing and image attachments. (MISP information sharing; MISP image objects) Here, the attacker aims to make the post-unlearning classifier misclassify a specific phishing page as legitimate, undermining downstream automated detection. In both scenarios, knowing the target’s label during attack construction does not mean that the model receives it during inference.
Public auxiliary-data sources. Publicly available ISIC2019 dermoscopic images carry diagnostic labels and provide a potential auxiliary-data source for skin-lesion classification; FLamby’s Fed-ISIC2019 provides a research benchmark for this federated task. (Fed-ISIC2019) For phishing detection, LNU-Phish provides screenshots and class information for legitimate and phishing webpages. (LNU-Phish) When the input formats and class definitions are compatible, these resources provide candidate samples for constructing the support and interference sets without accessing other participants’ private training data.
Control over client-side calibration. In these scenarios, we consider federated unlearning systems that support sample-level deletion and allow the relevant clients to continue participating in local calibration. Malicious clients incorporate support and interference samples during training, subsequently request deletion of the support records, and compute local calibration updates using enhanced interference samples with unchanged labels. The server receives model updates and performs the established calibration and aggregation procedures. These operations use malicious clients’ control over their own data and deletion requests, requiring neither server control nor additional server interfaces.
Critical Weakness 2: Evaluation against Existing Defenses
We evaluate BURST against Krum, Trimmed Mean, and FLAME on MNIST, distinguishing defenses applied during federated training from those applied during unlearning. BURST retains ASRs of 60.00%–75.00% under the evaluated training-stage defenses and 68.18%–72.73% under the evaluated unlearning-stage defenses.
Defense settings. We evaluate Krum, Trimmed Mean, and FLAME when applied only during federated training. We separately evaluate Trimmed Mean and FLAME when applied only during unlearning, directly examining whether defenses at the reconstruction and calibration stage prevent the attack. The results are as follows:
Attack effectiveness under defenses. When defenses operate only during training, BURST achieves ASRs of 75.00%, 63.64%, and 60.00% against Krum, Trimmed Mean, and FLAME, respectively. When defenses operate only during unlearning, ASRs are 72.73% against Trimmed Mean and 68.18% against FLAME. Thus, successful attacks persist even when defenses are applied directly at the unlearning stage.
The evaluated defenses do not eliminate BURST in these settings, motivating protection that explicitly accounts for attacks during unlearning. In the revised manuscript, we report these defense evaluations and distinguish their placement during training and unlearning.