English(EN) Mitigating Black-Box Score-Based Query Attacks via Gradient Confusion

新的防御方法保护机器学习模型免受黑盒查询攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了一种名为梯度混淆防御（GCD）的新防御机制，以保护机器学习模型免受基于分数的黑盒查询攻击。该方法无需重新训练模型，通过改变返回给攻击者的概率向量来起作用。GCD旨在通过使暴露的logit梯度与真实的对抗性损失梯度不对齐，来增加对手构造对抗性样本的复杂性。在CIFAR-10和ImageNet等数据集上，使用ResNet和ViT等架构进行的理论分析和实验表明，GCD在不影响预测准确性的情况下，能有效增强对最先进攻击的鲁棒性。 AI

影响增强了已部署的机器学习模型在面对复杂对抗性攻击时的安全性。

排序理由学术论文，详细介绍了缓解机器学习模型对抗性攻击的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了缓解机器学习模型对抗性攻击的新方法。[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.AI TIER_1 English(EN) · Ali Javeri, Javad Hezareh, Radin Shahdaei, AmirMahdi Sadeghzadeh · 2026-10-15 04:00

通过梯度混淆缓解黑盒基于分数的查询攻击

arXiv:2610.17382v1 Announce Type: cross Abstract: Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repeated model queries to craft adversarial examples, requiring neither access to model parameters nor architecture…

本文如何被排名

报道来源 [1]

通过梯度混淆缓解黑盒基于分数的查询攻击

相关实体

相关话题