应对后门攻击的深度学习人脸识别防御技巧集
A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks
AI 导读
一篇 arXiv 技术报告针对训练数据可能来自被投毒第三方数据的行业威胁模型，提出三种防御数据投毒后门攻击的实用技巧。其中一种在训练时检测被投毒身份，另两种在推理时过滤可疑输入以阻止信息回传给攻击者。每种方法均给出动机、算法与计算开销，并在真实人脸识别工作负载上评估，旨在为系统提供商提供可落地的加固手段。
正文 · 原文
Abstract:The protection of mature, multi-stage Face Recognition Systems is crucial to system providers. This technical report targets the threat model most relevant to industry practitioners: although model training is performed in-house, training data is sourced from possibly-compromised third parties. Given this setting, we present three practical defense "tricks" against data poisoning-based backdoor attacks. The first operates at training-time, detecting poisoned identities during training or prior to a pipeline's deployment. The last two operate at inference-time, filtering suspicious inputs before an answer can be sent back to a potential attacker. Each method is presented with their motivation, algorithms and computational impact, and evaluated on realistic face recognition workloads. Our goal is to provide actionable hardening techniques to system providers.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.06412 [cs.CV] |
| (or arXiv:2611.06412v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06412 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Quentin Le Roux [view email]
[v1]
Wed, 4 Nov 2026 12:12:32 UTC (1,132 KB)
来源：arXiv cs.AI · arxiv.org