PulseAugur
中
实时 07:57:59

新方法增强了针对MLLM和视觉模型的对抗攻击的迁移性

研究人员开发了新的方法来提高对抗性攻击针对多模态大语言模型(MLLM)和视觉语言模型的迁移性。第一种方法IAU-FOA在全局和局部层面匹配对抗样本和目标样本,使用最优传输进行细粒度特征匹配,并通过视觉不变性增强来提高跨不同视觉编码器的泛化能力。第二种方法LI-Boost侧重于增强对抗性扰动中的局部不变性,证明了这种局部不变性与跨各种模型架构甚至商业视觉API的迁移性提高之间存在正相关。 AI

影响 这些进展可能导致针对多模态人工智能系统的对抗性攻击的防御能力得到增强。

排序理由 该集群包含两篇学术论文,详细介绍了提高对抗攻击迁移性的新方法。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新方法增强了针对MLLM和视觉模型的对抗攻击的迁移性

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含两篇学术论文,详细介绍了提高对抗攻击迁移性的新方法。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
46 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Xiaojun Jia, Simeng Qin, Yiming Li, Jie Liao, Sensen Gao, Ke Ma, Yang Liu, Xiaochun Cao ·

    面向闭源多模态大模型的迁移性对抗攻击的视觉不变性增强特征最优对齐

    arXiv:2610.06977v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-source surrogate models are accessible. Existing targeted transfer attacks mainly al…

  2. arXiv cs.CV TIER_1 English(EN) · Bohan Liu, Xiaosen Wang ·

    提升局部不变性以获得更好的对抗可迁移性

    arXiv:2503.06140v3 Announce Type: replace Abstract: Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enhance adv…