使用卷积自编码器防御对抗攻击
Defense Against Adversarial Attacks using Convolutional Auto-Encoders
AI总结：
针对深度学习模型易受对抗扰动影响的问题，提出基于卷积自编码器的防御方法，通过重建输入图像消除扰动并恢复分类准确率。
摘要：
深度学习模型尽管在许多任务上取得了最先进的性能，却容易受到对抗攻击的影响，这类攻击利用其架构中固有的漏洞。对抗攻击通过难以察觉的扰动操纵输入数据，导致模型错误分类数据或产生错误输出。本研究以增强目标分类器模型抵御对抗攻击的鲁棒性为基础。为实现这一目标，采用了一种基于卷积自编码器的方法，有效对抗施加于输入图像的对抗扰动。通过生成与输入图像高度相似的图像，所提出的方法旨在恢复模型的准确率。
英文摘要：
Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with imperceptible perturbations, causing the model to misclassify the data or produce erroneous outputs. This work is based on enhancing the robustness of targeted classifier models against adversarial attacks. To achieve this, an convolutional autoencoder-based approach is employed that effectively counters adversarial perturbations introduced to the input images. By generating images closely resembling the input images, the proposed methodology aims to restore the model's accuracy.
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。
