Summary of Robust Vaes Via Generating Process Of Noise Augmented Data, by Hiroo Irobe et al.
Robust VAEs via Generating Process of Noise Augmented Data
by Hiroo Irobe, Wataru Aoki, Kimihiro Yamazaki, Yuhui Zhang, Takumi Nakagawa, Hiroki Waida, Yuichiro Wada, Takafumi Kanamori
First submitted to arxiv on: 26 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed study focuses on enhancing the defensive mechanisms of generative models, specifically Variational Auto-Encoders (VAEs), against adversarial attacks. Contrary to existing literature, preliminary experiments revealed that noise injection did not improve robustness and even degraded representation quality. A novel framework is introduced to regularize latent space divergence between original and noise-augmented data, boosting defense against adversarial attacks. The approach, termed Robust Augmented Variational Auto-ENcoder (RAVEN), demonstrates superior performance in resisting adversarial inputs on benchmark datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study aims to improve the defensive capabilities of generative models like VAEs against fake or malicious inputs. Initially, researchers tried adding noise to training data but found it didn’t make the models stronger and even made them worse. To fix this, a new way was developed to control how the model learns from both real and noisy data. This new method, called RAVEN, can help keep VAEs safe from attacks. |
Keywords
* Artificial intelligence * Boosting * Encoder * Latent space
