English(EN) AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation

新的AdvNav攻击目标是视觉语言导航系统

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-13 04:03

研究人员开发了AdvNav，一个新颖的黑盒对抗性攻击框架，旨在破坏视觉语言导航（VLN）系统。与先前需要白盒访问或专注于单步任务的方法不同，AdvNav在没有模型梯度的情况下运行，并针对顺序感知-行动循环。它利用双粒度行为反馈机制，结合轨迹和动作级别的性能得分，来指导一个迭代发现破坏性噪声配置的优化策略。评估表明，AdvNav在R2R数据集上针对基于Transformer和基于LLM的VLN模型取得了很高的攻击成功率，突显了当前系统存在的重大漏洞。 AI

影响强调了VLN模型中关键的感知漏洞，可能推动对更具弹性的AI导航系统的研究。

排序理由详细介绍AI系统新对抗性攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍AI系统新对抗性攻击方法的学术论文。[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: 87 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 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-07-13 04:03

AdvNav：行为引导的黑盒视觉语言导航对抗性攻击

Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances. Most existing methods rely on white-box access to target model gradients, which is often unrealistic for real-world deployed systems and computationally e…

本文如何被排名

报道来源 [1]

AdvNav：行为引导的黑盒视觉语言导航对抗性攻击

相关实体

相关话题