# PUREVQ-GAN: Defending Data Poisoning Attacks through Vector-Quantized Bottlenecks

arXiv: https://arxiv.org/abs/2509.25792 · HTML: https://mlsanity.com/paper/2509.25792/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 8 of 8)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching](https://mlsanity.com/paper/2009.02276/) (2020)
- [Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information](https://mlsanity.com/paper/2204.05255/) (2022)
- [Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability](https://mlsanity.com/paper/2005.00191/) (2020)
- [Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks](https://mlsanity.com/paper/2208.10224/) (2022)
- [PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics](https://mlsanity.com/paper/2405.18627/) (2024)

## Abstract (arXiv)

We introduce PureVQ-GAN, a defense against data poisoning that forces backdoor triggers through a discrete bottleneck using Vector-Quantized VAE with GAN discriminator. By quantizing poisoned images through a learned codebook, PureVQ-GAN destroys fine-grained trigger patterns while preserving semantic content. A GAN discriminator ensures outputs match the natural image distribution, preventing reconstruction of out-of-distribution perturbations. On CIFAR-10, PureVQ-GAN achieves 0% poison success rate (PSR) against Gradient Matching and Bullseye Polytope attacks, and 1.64% against Narcissus while maintaining 91-95% clean accuracy. Unlike diffusion-based defenses requiring hundreds of iterative refinement steps, PureVQ-GAN is over 50x faster, making it practical for real training pipelines.