# NNoculation: Catching BadNets in the Wild

arXiv: https://arxiv.org/abs/2002.08313 · HTML: https://mlsanity.com/paper/2002.08313/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks](https://mlsanity.com/paper/2206.08514/) (2022)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks](https://mlsanity.com/paper/2210.00108/) (2022)
- [Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection](https://mlsanity.com/paper/2307.05422/) (2023)
- [DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data](https://mlsanity.com/paper/2503.21305/) (2025)
- [MISA: Online Defense of Trojaned Models using Misattributions](https://mlsanity.com/paper/2103.15918/) (2021)
- [An Upper Bound for the Distribution Overlap Index and Its Applications](https://mlsanity.com/paper/2212.08701/) (2022)
- [Application of BadNets in Spam Filters](https://mlsanity.com/paper/2307.09649/) (2023)

## Abstract (arXiv)

This paper proposes a novel two-stage defense (NNoculation) against backdoored neural networks (BadNets) that, repairs a BadNet both pre-deployment and online in response to backdoored test inputs encountered in the field. In the pre-deployment stage, NNoculation retrains the BadNet with random perturbations of clean validation inputs to partially reduce the adversarial impact of a backdoor. Post-deployment, NNoculation detects and quarantines backdoored test inputs by recording disagreements between the original and pre-deployment patched networks. A CycleGAN is then trained to learn transformations between clean validation and quarantined inputs; i.e., it learns to add triggers to clean validation images. Backdoored validation images along with their correct labels are used to further retrain the pre-deployment patched network, yielding our final defense. Empirical evaluation on a comprehensive suite of backdoor attacks show that NNoculation outperforms all state-of-the-art defenses that make restrictive assumptions and only work on specific backdoor attacks, or fail on adaptive attacks. In contrast, NNoculation makes minimal assumptions and provides an effective defense, even under settings where existing defenses are ineffective due to attackers circumventing their restrictive assumptions.