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

December 13, 2024 ยท Declared Dead ยท ๐Ÿ› 2025 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Alireza Furutanpey, Pantelis A. Frangoudis, Patrik Szabo, Schahram Dustdar arXiv ID 2412.10265 Category cs.LG: Machine Learning Cross-listed cs.DC, cs.NI, eess.IV Citations 2 Venue 2025 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) Last Checked 4 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted