https://xiaokunduan.github.io/tags/series/Recent content in Series on Adversarial Network & RobustnessHugo -- 0.159.0en-usSat, 13 Sep 2025 00:00:00 +0000https://xiaokunduan.github.io/posts/adversarial-robustness-series/Sat, 13 Sep 2025 00:00:00 +0000https://xiaokunduan.github.io/posts/adversarial-robustness-series/A shorter, more readable 5-part path through adversarial robustness: motivation, theory, attacks, defenses, and high-stakes deployment.https://xiaokunduan.github.io/posts/part-1-why-ai-is-fragile/Mon, 08 Sep 2025 00:00:00 +0000https://xiaokunduan.github.io/posts/part-1-why-ai-is-fragile/Why high-performing AI systems can still fail under tiny perturbations, and why that fragility matters.https://xiaokunduan.github.io/posts/part-2-what-robustness-really-means/Tue, 09 Sep 2025 00:00:00 +0000https://xiaokunduan.github.io/posts/part-2-what-robustness-really-means/A theory-first guide to Bayes error, gradients, and loss landscapes as the foundation for robustness.https://xiaokunduan.github.io/posts/part-3-how-attacks-evolved/Wed, 10 Sep 2025 00:00:00 +0000https://xiaokunduan.github.io/posts/part-3-how-attacks-evolved/From FGSM and PGD to 3D attacks, adversarial viewpoints, and explainability attacks.https://xiaokunduan.github.io/posts/part-4-how-we-defend-models/Thu, 11 Sep 2025 00:00:00 +0000https://xiaokunduan.github.io/posts/part-4-how-we-defend-models/A compact map of the main defense routes: adversarial training, data-centric methods, certification, and efficient purification.https://xiaokunduan.github.io/posts/part-5-robustness-in-modern-high-stakes-settings/Fri, 12 Sep 2025 00:00:00 +0000https://xiaokunduan.github.io/posts/part-5-robustness-in-modern-high-stakes-settings/Why robustness becomes a systems problem in modern architectures and high-cost applications.