RepObE: Representation Learning-Enhanced Obfuscation Encryption Modular Semantic Task Framework
Authors: Limei Lin, Jinpeng Xu, Xiaoding Wang, Liang Chen, Sun-Yuan Hsieh, Jie Wu
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrate that our method surpasses existing techniques by more than 2% in resisting model inversion attacks on classification tasks. Visually, our method excels with minimal decipherable images for attackers. It also shows a 3% to 5% improvement in countering adversarial attacks on classification tasks. |
| Researcher Affiliation | Collaboration | 1College of Computer and Cyber Security, Fujian Provincial Key Laboratory of Network Security and Cryptology, Fujian Normal University, Fuzhou 350117, China 2Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701, Taiwan 3China Telecom Cloud Computing Research Institute, Beijing, 100088, China 4Department of Computer and Information Sciences, Temple University, PA 19122, USA |
| Pseudocode | Yes | Algorithm 1 Rep Ob E Training Algorithm |
| Open Source Code | No | The paper does not provide concrete access to source code. It mentions supplementary materials for the system model and experimental settings but does not state that code is provided. |
| Open Datasets | Yes | The experiments in this study utilized the MNIST and CIFAR-10 datasets, representing handwritten digit classification and more complex color image classification tasks, respectively. |
| Dataset Splits | No | The paper mentions using MNIST and CIFAR-10 datasets for classification tasks but does not explicitly provide specific training/test/validation dataset splits within the main text. It defers to supplementary materials for 'experimental settings designed in this study', but these are not available in the provided text. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | The Signal-to-Noise Ratio (SNR) range was set from 7 to 23... adversarial training (ϵ = 0.016)... (ϵ = 0.016, step size 0.0032, 5 iterations). |