几篇近期研究论文探讨了增强深度神经网络对抗鲁棒性的新方法。这些研究引入了诸如结合经验和认证防御的集成方法、噪声和双边滤波器的协同使用以及用于模拟对抗不确定性的贝叶斯框架等技术。此外，一篇论文提出了一个新的分类器，该分类器在判别能力和鲁棒性之间取得平衡，而另一篇则侧重于能够处理非加性扰动的对抗净化方法。 AI
影响 这些多样化的方法旨在提高 AI 系统对抗恶意攻击的可靠性和安全性，有可能使其在安全关键型应用中得到更广泛的应用。
排序理由 多篇在 arXiv 上发表的学术论文，详细介绍了深度学习模型对抗鲁棒性的新方法。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
arXiv:2606.01437v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are highly susceptible to adversarial perturbations, leading to extensive research on robustness for safety-critical applications. State-of-the-art empirical defense mechanisms improve the robustness of…
arXiv:2606.02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment. Existing techniques to enhance deep network robustness rely on adversarial training, an approach that is powe…
arXiv:2606.01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations. In this work, we identify that part of this vulnerability stems from the sensitivity of the widely used fully connected (FC) classifiers to such perturbat…
arXiv:2510.09288v2 Announce Type: replace Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge. Traditional defenses, such as adversarial training, typically robustify models by minimizing a worst-case loss. …
arXiv:2510.14025v2 Announce Type: replace Abstract: Adversarial purification has achieved great success in combating adversarial image perturbations, which are usually assumed to be additive. However, non-additive adversarial perturbations such as blur, occlusion, and distortion …