Rapid Plug-in Defenders（快速插件式防御器）
Rapid Plug-in Defenders
AI总结：
针对深度神经网络易受对抗攻击且现有鲁棒性增强方法耗时的问题，提出CeTaD方法，通过微调预训练Transformer归一化层参数，实现不改动目标模型的快速插件式防御，具备良好适应性与可迁移性。
摘要：
在日常服务领域，深度神经网络的部署凸显了其可靠性的至关重要性。然而，这些网络易受主要为规避型的对抗攻击的脆弱性，对其功能构成了令人担忧的威胁。增强鲁棒性的常用方法包括高强度对抗训练或利用从干净数据中学到的知识，这两种方法都需要大量计算资源。这种固有的耗时特性严重限制了大型基础模型快速应对对抗扰动的敏捷性。为解决这一挑战，本文聚焦于Rapid Plug-in Defender（RaPiD，快速插件式防御器）问题，旨在在不改变已部署模型的情况下快速应对对抗扰动。受预训练transformer模型的泛化能力和通用计算能力的启发，我们提出了一种名为CeTaD（将预训练Transformer视为防御器）的新型RaPiD方法，针对高效计算进行了优化。CeTaD使用有限的干净样本和对抗样本，策略性地微调防御器内部的归一化层参数。我们的评估重点是在涉及单次（one-shot）对抗样本的场景中，评估CeTaD的有效性、可迁移性以及不同组件的影响。所提出的方法能够在不改变目标模型和干净训练数据的情况下，快速适应各种攻击和不同的应用场景。我们还探讨了不同训练数据条件对CeTaD性能的影响。值得注意的是，CeTaD在可微服务模型中展现出适应性，并证明了持续学习的潜力。
英文摘要：
In the realm of daily services, the deployment of deep neural networks underscores the paramount importance of their reliability. However, the vulnerability of these networks to adversarial attacks, primarily evasion-based, poses a concerning threat to their functionality. Common methods for enhancing robustness involve heavy adversarial training or leveraging learned knowledge from clean data, both necessitating substantial computational resources. This inherent time-intensive nature severely limits the agility of large foundational models to swiftly counter adversarial perturbations. To address this challenge, this paper focuses on the Rapid Plug-in Defender (RaPiD) problem, aiming to rapidly counter adversarial perturbations without altering the deployed model. Drawing inspiration from the generalization and the universal computation ability of pre-trained transformer models, we propose a novel method termed CeTaD (Considering Pre-trained Transformers as Defenders) for RaPiD, optimized for efficient computation. CeTaD strategically fine-tunes the normalization layer parameters within the defender using a limited set of clean and adversarial examples. Our evaluation centers on assessing CeTaD's effectiveness, transferability, and the impact of different components in scenarios involving one-shot adversarial examples. The proposed method is capable of rapidly adapting to various attacks and different application scenarios without altering the target model and clean training data. We also explore the influence of varying training data conditions on CeTaD's performance. Notably, CeTaD exhibits adaptability across differentiable service models and proves the potential of continuous learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
