# Adversarial Robustness of Bottleneck Injected Deep Neural Networks for Task-Oriented Communication

arXiv: https://arxiv.org/abs/2412.10265 · HTML: https://mlsanity.com/paper/2412.10265/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 17 of 17)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [Torchattacks: A PyTorch Repository for Adversarial Attacks](https://mlsanity.com/paper/2010.01950/) (2020)
- [EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples](https://mlsanity.com/paper/1709.04114/) (2017)
- [Lossy Compression for Lossless Prediction](https://mlsanity.com/paper/2106.10800/) (2021)
- [End-to-end Learning of Compressible Features](https://mlsanity.com/paper/2007.11797/) (2020)
- [Supervised Compression for Resource-Constrained Edge Computing Systems](https://mlsanity.com/paper/2108.11898/) (2021)
- [Adversarial Images for Variational Autoencoders](https://mlsanity.com/paper/1612.00155/) (2016)
- [FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression](https://mlsanity.com/paper/2403.16677/) (2024)
- [Task-Oriented Communication Design at Scale](https://mlsanity.com/paper/2305.08481/) (2023)

## Built on by (most cited first, 1 of 1)

- [Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems](https://mlsanity.com/paper/2504.20198/) (2025)

## Abstract (arXiv)

This paper investigates the adversarial robustness of Deep Neural Networks (DNNs) using Information Bottleneck (IB) objectives for task-oriented communication systems. We empirically demonstrate that while IB-based approaches provide baseline resilience against attacks targeting downstream tasks, the reliance on generative models for task-oriented communication introduces new vulnerabilities. Through extensive experiments on several datasets, we analyze how bottleneck depth and task complexity influence adversarial robustness. Our key findings show that Shallow Variational Bottleneck Injection (SVBI) provides less adversarial robustness compared to Deep Variational Information Bottleneck (DVIB) approaches, with the gap widening for more complex tasks. Additionally, we reveal that IB-based objectives exhibit stronger robustness against attacks focusing on salient pixels with high intensity compared to those perturbing many pixels with lower intensity. Lastly, we demonstrate that task-oriented communication systems that rely on generative models to extract and recover salient information have an increased attack surface. The results highlight important security considerations for next-generation communication systems that leverage neural networks for goal-oriented compression.