paper-with-me

Papers

Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning

2026-03-11 · Xian Qin, Xue Yang, Xiaohu Tang arxiv

While Secure Aggregation (SA) protects update confidentiality in Cross-silo Federated Learning, it fails to guarantee aggregation integrity, allowing malicious servers to silently omit or tamper with updates. Existing verifiable aggregation schemes rely on heavyweight cryptography (e.g., ZKPs, HE), incurring computational costs that scale poorly with model size. In this paper, we propose a lightweight architecture that shifts from extrinsic cryptographic proofs to \textit{Intrinsic Proofs}. We repurpose backdoor injection to embed verification signals directly into model parameters. By harnessing Catastrophic Forgetting, these signals are robust for immediate verification yet ephemeral, naturally decaying to preserve final model utility. We design a randomized, single-verifier auditing framework compatible with SA, ensuring client anonymity and preventing signal collision without trusted third parties. Experiments on SVHN, CIFAR-10, and CIFAR-100 demonstrate high detection probabilities against malicious servers. Notably, our approach achieves over $1000\times$ speedup on ResNet-18 compared to cryptographic baselines, effectively scaling to large models.

📄 PDF Abstract BibTeX arXiv:2603.10692

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

TRAPDOOR: Repurposing backdoors to detect dataset bias in machine learning-based genomic analysis

2021-08-14 · Esha Sarkar, Michail Maniatakos

Machine Learning (ML) has achieved unprecedented performance in several applications including image, speech, text, and data analysis. Use of ML to understand underlying patterns in gene mutations (genomics) has far-reac…

BIG-bench Machine LearningDiagnostic

Securing Private Federated Learning in a Malicious Setting: A Scalable TEE-Based Approach with Client Auditing

2025-09-10 · Shun Takagi, Satoshi Hasegawa arxiv

In cross-device private federated learning, differentially private follow-the-regularized-leader (DP-FTRL) has emerged as a promising privacy-preserving method. However, existing approaches assume a semi-honest server an…

Federated Learning

A Little Is Enough: Circumventing Defenses For Distributed Learning

2019-02-16 · NeurIPS 2019 12 · Moran Baruch, Gilad Baruch, Yoav Goldberg

Distributed learning is central for large-scale training of deep-learning models. However, they are exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous att…

Manipulating Trajectory Prediction with Backdoors

2023-12-21 · Kaouther Messaoud, Kathrin Grosse, Mickael Chen, Matthieu Cord 외

Autonomous vehicles ought to predict the surrounding agents' trajectories to allow safe maneuvers in uncertain and complex traffic situations. As companies increasingly apply trajectory prediction in the real world, secu…

Autonomous VehiclesPredictionTrajectory Prediction

A Zero-Shot Learning Approach for Ephemeral Gully Detection from Remote Sensing using Vision Language Models

2025-03-03 · Seyed Mohamad Ali Tousi, Ramy Farag, Jacket Demby's, Gbenga Omotara 외

Ephemeral gullies are a primary cause of soil erosion and their reliable, accurate, and early detection will facilitate significant improvements in the sustainability of global agricultural systems. In our view, prior re…

Transfer Learningzero-shot-classificationZero-Shot Learning