https://111qqz.com/tags/robustness/Recent content in Robustness on 111qqz的小窝Hugo -- gohugo.iozh-cnhust.111qqz@gmail.com (111qqz)hust.111qqz@gmail.com (111qqz)© 2011-2026 111qqzFri, 16 Oct 2026 22:25:00 +0800https://111qqz.com/2026/10/adversarial-attacks-fgsm/Fri, 16 Oct 2026 22:25:00 +0800hust.111qqz@gmail.com (111qqz)https://111qqz.com/2026/10/adversarial-attacks-fgsm/<h2 class="relative group">起因 <div id="起因" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#%e8%b5%b7%e5%9b%a0" aria-label="锚点">#</a> </span> </h2> <p><a href="https://111qqz.com/2026/10/rethinking-generalization-random-labels/" >上一篇</a>写完随机标签实验之后，我对泛化的理解更新了一轮：模型有能力记住随机标签，不代表它面对真实数据时只会死记硬背。capacity、learned function 和 generalization 是三件不同的事。</p>