用后门信号实现轻量级模型聚合验证，速度快上千倍。
Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning
- 将后门注入转化为内生验证信号，嵌入模型参数中。
- 在ResNet-18上比加密方案快1000倍以上，检测率高。
- 无需可信第三方，适合大规模跨孤岛联邦学习场景。
尽管安全聚合（SA）保护了跨孤岛联邦学习中的更新隐私，但无法保证聚合完整性，恶意服务器可静默删除或篡改更新。现有可验证聚合方案依赖重型密码学（如零知识证明、同态加密），计算开销随模型规模增长而急剧上升。本文提出一种轻量级架构，将外在密码学证明转向内在证明：通过重用后门注入，在模型参数中嵌入验证信号。利用灾难性遗忘机制，这些信号可即时验证却短暂存在，自然衰减以保障最终模型效用。设计了随机化单验证器审计框架，兼容安全聚合，确保客户端匿名性，且无需可信第三方即可防信号冲突。在SVHN、CIFAR-10和CIFAR-100上的实验表明，对恶意服务器具备高检测概率。尤其在ResNet-18上，相比加密基线提速超1000倍，有效支持大模型扩展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。