English(EN) What Makes Adversarial Examples Transfer Across Deepfake Detectors?

基于兼容性的对抗性样本可跨深度伪造检测器迁移

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

研究人员调查了对抗性样本在不同深度伪造检测器之间的迁移性，发现源模型和目标模型之间的兼容性显著影响攻击成功率。他们对60个检测器进行的受控评估显示，共享的骨干网络、架构家族、预训练方案或训练数据会导致更高的迁移率。研究还指出，跨多个源的平均攻击成功率可能会低估目标模型的脆弱性，当排除特定的兼容性因素时，多源预言机可以实现更高的成功率。 AI

影响研究结果确立了源-目标兼容性和源模型选择对于可信的基于迁移的黑盒鲁棒性评估至关重要。

排序理由学术论文，详细介绍了深度伪造检测中对抗性迁移性的受控评估。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了深度伪造检测中对抗性迁移性的受控评估。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira · 2026-09-10 04:00

深度伪造检测器之间的对抗性样本为何能够迁移？

arXiv:2609.10002v1 Announce Type: new Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target com…

本文如何被排名

报道来源 [1]

深度伪造检测器之间的对抗性样本为何能够迁移？

相关实体

相关话题