PulseAugur
中
实时 12:07:42
English(EN) Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models

新的防御机制提高了 VLM 对抗对抗性攻击的鲁棒性

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员开发了一种名为高噪声漂移门控 (High-Noise Drift Gating) 的新防御机制，以提高视觉语言模型 (VLM) 对抗对抗性攻击的鲁棒性。该方法识别出 CLIP 等 VLM 中的一个关键噪声区域转换，在该区域，对抗性表示在较高噪声水平下比干净表示明显更不稳定。通过利用这种不稳定性作为信号，系统仅在必要时选择性地应用现有的测试时防御，从而同时提高干净精度和对抗鲁棒性。 AI

影响 这项研究提供了一种更有效的方法来保护视觉语言模型免受对抗性操纵，有可能提高它们在实际应用中的可靠性。

排序理由 该集群包含一篇详细介绍提高人工智能模型安全性新方法的学术论文。

在 arXiv cs.CV 阅读 →

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

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Hashmat Shadab Malik, Muzammal Naseer, Salman Khan ·

    Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models

    arXiv:2606.03730v1 Announce Type: new Abstract: Vision-language models (VLMs) such as CLIP show strong zero-shot generalization but remain highly vulnerable to adversarial attacks. Adversarial training improves robustness but is computationally expensive, motivating test-time def…

  2. arXiv cs.CV TIER_1 English(EN) · Salman Khan ·

    Beyond False Stability: High-Noise Drift Gating for Test-Time Adversarial Defenses in Vision-Language Models

    Vision-language models (VLMs) such as CLIP show strong zero-shot generalization but remain highly vulnerable to adversarial attacks. Adversarial training improves robustness but is computationally expensive, motivating test-time defenses. Recent approaches exploit how CLIP's visu…

相关实体

相关话题