Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions

• URL: http://arxiv.org/abs/2605.20341v1
• Date: Tue, 19 May 2026 18:00:39 GMT
• Title: Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions
• Abstract summary: Federated learning systems must support data deletion requests to comply with privacy regulations.<n>We present HF-KCU, a method that removes a client's contribution by approximating the influence through conjugate iterations in Krylov subspaces.<n>We provide convergence guarantees showing that the Krylov approximation error decreases as O((k 1/2-1)/(k1/2+1) where k is the Hessian condition number.
• Score: 2.5565719921628443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive. We present HF-KCU, a method that removes a client's contribution by approximating the influence function through conjugate gradient iterations in Krylov subspaces, reducing complexity from O(d^3) to O(kd) where k<<d.A causal weighting mechanism ensures that only clients holding the deleted data receive parameter updates, preventing spurious changes to unaffected clients. Our method is designed to handle bounded adversarial perturbations to the Hessian and gradient, providing graceful degradation under realistic threat models. We validate HF-KCU across convolutional (ResNet-18, SimpleCNN) and transformer (ViT-Lite) architectures on CIFAR-10, MNIST, and Fashion-MNIST. On CIFAR-10 under Dirichlet (alpha=0.5) partitioning, HF-KCU achieves 47.75 times speedup over retraining while maintaining test accuracy within 0.60% of the rational baseline(71.16 vs 71.76 %). Membership inference attacks on the forget set yield success rates of 0.499 matching the retrained model and confirming effective privacy restoration. We provide convergence guarantees showing that the Krylov approximation error decreases as O((k ^1/2-1)/(k^1/2+1)) where k is the Hessian condition number. The causal weighting mechanism ensures surgical updates, where only clients holding deleted data are modified, preserving model quality for unaffected participants and avoiding the instability of gradient-based approaches in asynchronous federated settings. This design provides interpretability as each update is directly traceable to the influence of the deleted data. The method's efficiency and precision make it suitable for production federated systems where deletion requests arrive asynchronously and computational budgets are constrained.

Related papers

• Correlation-Guided Fast Machine Unlearning via Hessian Analysis [15.622259863184295]
  Existing unlearning techniques require repeated expensive Hessian-inverse-vector computations for each data point removal.<n>We introduce a computationally efficient unlearning framework that identifies correlated data points in the training set and applies a theoretically derived closed-form parameter update rule.<n>Our method establishes theoretical guarantees and ensures numerical stability through Hessian damping.
  arXiv  Detail & Related papers  (2026-09-11T09:21:30Z)
• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• DECAF: De-Clustering for Adaptive Representational Unlearning [13.298390892944221]
  We propose DECAF (DE-Clustering for Adaptive Forgetting), a post-hoc method that operates only on the forget set and is designed to break the cluster.<n>On CIFAR-10 with ResNet-18, DECAF attains 0.10% forget-class accuracy, 79.4% retain accuracy, and an AUS of 0.88, surpassing all other baselines.
  arXiv  Detail & Related papers  (2026-07-27T02:11:58Z)
• Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration [76.08899010904652]
  CapCal is a training-free framework that mechanically decouples positional bias from ranking decisions.<n>It achieves superior performance among training-free methods while preserving single-pass efficiency.
  arXiv  Detail & Related papers  (2026-04-11T10:47:22Z)
• Variational Feature Compression for Model-Specific Representations [16.34000934736747]
  Deep learning inference is increasingly deployed in shared and cloud-based settings.<n>A growing concern is input repurposing, in which data submitted for one task is reused by unauthorized models for another.<n>We propose a feature extraction framework that suppresses cross-model transfer while preserving accuracy for a designated classifier.
  arXiv  Detail & Related papers  (2026-04-08T03:34:46Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning [0.6524460254566904]
  Federated learning (FL) enables collaborative model training while preserving data privacy.<n>It remains vulnerable to malicious clients who compromise model integrity through Byzantine attacks, data poisoning, or adaptive adversarial behaviors.<n>We propose FLARE, an adaptive reputation-based framework that transforms client reliability assessment from binary decisions to a continuous, multi-dimensional trust evaluation.
  arXiv  Detail & Related papers  (2025-11-18T17:57:40Z)
• FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learning [7.461859467262201]
  Federated Learning (FL) enables collaborative model training across decentralized clients.<n>FL suffers from significant communication overhead due to the frequent exchange of high-dimensional model updates over constrained networks.<n>We present FedSparQ, a lightweight compression framework that dynamically sparsifies the gradient of each client.
  arXiv  Detail & Related papers  (2025-11-05T12:38:08Z)
• A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning [43.847168319564844]
  We propose an FL backdoor defense framework, named CLIP-Fed, that utilizes the zero-shot learning capabilities of vision-language pre-training models.<n>Our scheme overcomes the limitations of Non-IID imposed on defense effectiveness by integrating pre-aggregation and post-aggregation defense strategies.
  arXiv  Detail & Related papers  (2025-08-14T03:39:54Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)
• Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design [76.29738151117583]
  Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. We model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk.
  arXiv  Detail & Related papers  (2021-05-10T08:02:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.