提出两种新方法，从神经网络输出反推输入图像。
Inverting Neural Networks: New Methods to Generate Neural Network Inputs from Prescribed Outputs
- 基于雅可比矩阵与根查找的前向反演方法
- 通过逐层反推并注入零空间随机向量生成输入
- 可生成高分类准确率的随机输入，揭示模型漏洞
神经网络的复杂映射关系难以理解。本文研究从特定输出反推输入图像的逆问题，期望这些图像包含与类别相关的可识别特征。提出两种通用方法：前向法基于输入图像的雅可比矩阵与根查找算法；后向法从顶层逐层反推，并在每层加入线性层零空间采样的随机向量。实验验证了方法在变压器架构和基于线性层的序列网络上的有效性。与以往方法不同，新方法能在所有情况下生成近似随机的输入图像，并实现接近完美的分类得分，揭示了底层网络的潜在脆弱性。因此，所提方法对解决逆映射问题提供了更全面的输入空间覆盖。
原文摘要 · Abstract (English)
Neural network systems describe complex mappings that can be very difficult to understand. In this paper, we study the inverse problem of determining the input images that get mapped to specific neural network classes. Ultimately, we expect that these images contain recognizable features that are associated with their corresponding class classifications. We introduce two general methods for solving the inverse problem. In our forward pass method, we develop an inverse method based on a root-finding algorithm and the Jacobian with respect to the input image. In our backward pass method, we iteratively invert each layer, at the top. During the inversion process, we add random vectors sampled from the null-space of each linear layer. We demonstrate our new methods on both transformer architectures and sequential networks based on linear layers. Unlike previous methods, we show that our new methods are able to produce random-like input images that yield near perfect classification scores in all cases, revealing vulnerabilities in the underlying networks. Hence, we conclude that the proposed methods provide a more comprehensive coverage of the input image spaces that solve the inverse mapping problem.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。