arXiv Artificial Intelligence

Neural Network Verification for Deep Joint Source-Channel Coding

2 hours ago 09.10.2026 07:00 👁 2 views
Neural Network Verification for Deep Joint Source-Channel Coding

Quick summary

arXiv:2610.11994v1 Announce Type: cross Abstract: 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:

Key takeaways

  • arXiv:2610.11994v1 Announce Type: cross Abstract: 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:

Why it matters

“Neural Network Verification for Deep Joint Source-Channel Coding” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗