English(EN) Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery

新框架应对持续学习中的后门攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员引入了一个新的持续学习框架，以应对顺序到达任务中后门攻击的挑战。该框架集成了样本净化、选择性恢复和鲁棒专家路由，以减轻灾难性遗忘，保持适应性，并防止恶意监督的吸收。提出的方法包括用于识别可疑样本的双原型净化（BPP），用于选择性恢复和伪标签校正的梯度差异鲁棒性优化（GDBRO），以及用于可靠专家路由的鲁棒特征一致性专家选择（RFCBES）。 AI

影响引入了一种新颖的方法来增强持续学习系统针对复杂攻击的安全性和鲁棒性。

排序理由详细介绍持续学习新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍持续学习新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Keyu Lin, Fei Ye, Qihe Liu, Shijie Zhou, Jiguo Yu · 2026-09-10 04:00

通过净化和选择性恢复实现后门攻击下持续学习的鲁棒动态扩展

arXiv:2609.06346v1 Announce Type: new Abstract: Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge. However, in practical scenarios, task streams collected from untrusted sources may contai…

本文如何被排名

报道来源 [1]

通过净化和选择性恢复实现后门攻击下持续学习的鲁棒动态扩展

相关实体

相关话题