# HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks

arXiv: https://arxiv.org/abs/2309.08549 · HTML: https://mlsanity.com/paper/2309.08549/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## 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, 24 of 24)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Attacks Which Do Not Kill Training Make Adversarial Learning Stronger](https://mlsanity.com/paper/2002.11242/) (2020)
- [Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization](https://mlsanity.com/paper/1708.08689/) (2017)
- [Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching](https://mlsanity.com/paper/2009.02276/) (2020)
- [Transferable Clean-Label Poisoning Attacks on Deep Neural Nets](https://mlsanity.com/paper/1905.05897/) (2019)
- [MetaPoison: Practical General-purpose Clean-label Data Poisoning](https://mlsanity.com/paper/2004.00225/) (2020)
- [RAB: Provable Robustness Against Backdoor Attacks](https://mlsanity.com/paper/2003.08904/) (2020)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff](https://mlsanity.com/paper/2011.09527/) (2020)
- [Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder](https://mlsanity.com/paper/1905.09027/) (2019)
- [Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability](https://mlsanity.com/paper/2005.00191/) (2020)
- [Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training](https://mlsanity.com/paper/2102.04716/) (2021)
- [On Adversarial Bias and the Robustness of Fair Machine Learning](https://mlsanity.com/paper/2006.08669/) (2020)
- [DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations](https://mlsanity.com/paper/2103.02079/) (2021)
- [Not All Poisons are Created Equal: Robust Training against Data Poisoning](https://mlsanity.com/paper/2210.09671/) (2022)
- [What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning](https://mlsanity.com/paper/2102.13624/) (2021)
- [Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks](https://mlsanity.com/paper/2208.10224/) (2022)
- [Poisoning Attacks on Fair Machine Learning](https://mlsanity.com/paper/2110.08932/) (2021)

## Built on by (most cited first, 1 of 1)

- [Fairshare Data Pricing via Data Valuation for Large Language Models](https://mlsanity.com/paper/2502.00198/) (2025)

## Abstract (arXiv)

While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary to exploit. In this work, we propose an efficient and robust training approach to defend against data poisoning attacks based on influence functions, named Healthy Influential-Noise based Training. Using influence functions, we craft healthy noise that helps to harden the classification model against poisoning attacks without significantly affecting the generalization ability on test data. In addition, our method can perform effectively when only a subset of the training data is modified, instead of the current method of adding noise to all examples that has been used in several previous works. We conduct comprehensive evaluations over two image datasets with state-of-the-art poisoning attacks under different realistic attack scenarios. Our empirical results show that HINT can efficiently protect deep learning models against the effect of both untargeted and targeted poisoning attacks.