Academic Journal
AdVAR-DNN: Adversarial Misclassification Attack on Collaborative DNN Inference
| Title: | AdVAR-DNN: Adversarial Misclassification Attack on Collaborative DNN Inference |
|---|---|
| Authors: | Yousefi, Shima, Mounesan, Motahare, Debroy, Saptarshi |
| Source: | 2025 IEEE 50th Conference on Local Computer Networks (LCN). :1-9 |
| Publication Status: | Preprint |
| Publisher Information: | IEEE, 2025. |
| Publication Year: | 2025 |
| Subject Terms: | FOS: Computer and information sciences, Cryptography and Security, Distributed, Parallel, and Cluster Computing, Distributed, Parallel, and Cluster Computing (cs.DC), Cryptography and Security (cs.CR) |
| Description: | In recent years, Deep Neural Networks (DNNs) have become increasingly integral to IoT-based environments, enabling realtime visual computing. However, the limited computational capacity of these devices has motivated the adoption of collaborative DNN inference, where the IoT device offloads part of the inference-related computation to a remote server. Such offloading often requires dynamic DNN partitioning information to be exchanged among the participants over an unsecured network or via relays/hops, leading to novel privacy vulnerabilities. In this paper, we propose AdVAR-DNN, an adversarial variational autoencoder (VAE)-based misclassification attack, leveraging classifiers to detect model information and a VAE to generate untraceable manipulated samples, specifically designed to compromise the collaborative inference process. AdVAR-DNN attack uses the sensitive information exchange vulnerability of collaborative DNN inference and is black-box in nature in terms of having no prior knowledge about the DNN model and how it is partitioned. Our evaluation using the most popular object classification DNNs on the CIFAR-100 dataset demonstrates the effectiveness of AdVAR-DNN in terms of high attack success rate with little to no probability of detection. |
| Document Type: | Article |
| DOI: | 10.1109/lcn65610.2025.11146344 |
| DOI: | 10.48550/arxiv.2508.01107 |
| Access URL: | http://arxiv.org/abs/2508.01107 |
| Rights: | STM Policy #29 CC BY NC ND |
| Accession Number: | edsair.doi.dedup.....c5f097cd83ca2cd4af9dff465df5aaa2 |
| Database: | OpenAIRE |
| DOI: | 10.1109/lcn65610.2025.11146344 |
|---|