发表机构
National Institute of Information and Communication Technology; George Mason University（信息通信研究机构; 乔治梅森大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对DeepJSCC解码器提出边界传播框架，扩展DNN验证技术适配其特殊组件，结合GloRo训练提升鲁棒性，在图像传输任务中实现更优认证效果且经硬件验证有效。
AI 中文摘要
深度联合信源信道编码（DeepJSCC）使用神经编解码器通过无线信道端到端传输数据，但在对抗性扰动和信道干扰下重建质量会急剧下降；目前尚无方法对DeepJSCC的这种下降进行形式化界定。我们提出首个用于验证DeepJSCC解码器的边界传播框架，可界定给定无线信道噪声区域内的最坏情况重建误差。现有深度神经网络（DNN）验证器不支持DeepJSCC解码器的三个组件：参数化整流线性激活函数（PReLU）、转置卷积和瑞利衰落。我们扩展了DNN验证中线性松弛优化的最新技术以适配PReLU，将转置卷积替换为其受限上采样后卷积的形式，并将瑞利衰落表述为直接前置到解码器的结构扰动，从而降低验证问题的维度。我们还实例化了 Lipschitz 正则化全局鲁棒性训练（记为GloRo），首次提升了全局鲁棒性并实现了对DeepJSCC模型的紧认证。在用于图像传输的DeepJSCC模型上，该全局鲁棒性训练流程结合结构编码，使中位数认证边界降低多达41%，且在信道估计误差为10度时，相比采用区间编码的GloRo，可认证的安全案例数量约为其十倍（192个对19个）。通过软件无线电设备上的正交频分复用（OFDM）实现进行空中验证，确认该认证在真实硬件上有效，无线电链路上观测到的最坏误差为0.082，而认证边界为0.128。
英文摘要
Deep joint source-channel coding (DeepJSCC) transmits data end-to-end over wireless channels using a neural encoder-decoder, but reconstruction quality can degrade sharply under adversarial perturbations and channel disturbances; no method formally bounds this degradation for DeepJSCC. We present the first bound-propagation framework for verifying DeepJSCC's decoder, bounding worst-case reconstruction error over a given wireless channel's noise region. Current deep neural network (DNN) verifiers do not support three DeepJSCC decoder components: parametric rectified linear activations (PReLU), transposed convolutions, and Rayleigh fading. We extend state-of-the-art techniques for optimization of linear relaxation in DNN verification for PReLU, replace the transposed convolution with its restricted upsample-then-convolution form, and formulate Rayleigh fading as a structural perturbation prepended directly into the decoder, thereby reducing the dimensionality of the verification problem. We also instantiate Lipschitz-regularized global robustness training, denoted GloRo, improving global robustness and enabling tight certification of DeepJSCC models for the first time. On DeepJSCC model for image transmission, this global robustness training procedure combined with structural encoding lowers the median certified bound by up to 41% and certifies about ten times more safe cases (192 against 19) than GloRo with interval encoding at a 10-degree error in channel estimation. Over-the-air validation with an orthogonal frequency-division multiplexing (OFDM) implementation on software-defined radio devices confirm the certificate holds on real hardware, with a worst observed error on radio link at 0.082 against a certified bound of 0.128.
