# Backdoor Attack and Defense for Deep Regression

arXiv: https://arxiv.org/abs/2109.02381 · HTML: https://mlsanity.com/paper/2109.02381/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 6 Sep 2021.

## Builds on (most cited first, 12 of 12)

- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [A Comprehensive Analysis of Deep Regression](https://mlsanity.com/paper/1803.08450/) (2018)
- [Neural networks for option pricing and hedging: a literature review](https://mlsanity.com/paper/1911.05620/) (2019)
- [Active Learning for Regression Using Greedy Sampling](https://mlsanity.com/paper/1808.04245/) (2018)
- [Dropout-based Active Learning for Regression](https://mlsanity.com/paper/1806.09856/) (2018)
- [Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks](https://mlsanity.com/paper/1904.06292/) (2019)
- [Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing](https://mlsanity.com/paper/2010.07489/) (2020)
- [Adversarial Learning: A Critical Review and Active Learning Study](https://mlsanity.com/paper/1705.09823/) (2017)
- [Detection of Backdoors in Trained Classifiers Without Access to the Training Set](https://mlsanity.com/paper/1908.10498/) (2019)
- [Deeply Learning Derivatives](https://mlsanity.com/paper/1809.02233/) (2018)
- [Robust and Active Learning for Deep Neural Network Regression](https://mlsanity.com/paper/2107.13124/) (2021)

## Built on by (most cited first, 6 of 6)

- [Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks](https://mlsanity.com/paper/2112.03350/) (2021)
- [BadGD: A unified data-centric framework to identify gradient descent vulnerabilities](https://mlsanity.com/paper/2405.15979/) (2024)
- [Temporal-Distributed Backdoor Attack Against Video Based Action Recognition](https://mlsanity.com/paper/2308.11070/) (2023)
- [Defending Deep Regression Models against Backdoor Attacks](https://mlsanity.com/paper/2411.04811/) (2024)
- [Backdoor Mitigation by Correcting the Distribution of Neural Activations](https://mlsanity.com/paper/2308.09850/) (2023)
- [Poisoning Attacks on Federated Learning for Autonomous Driving](https://mlsanity.com/paper/2405.01073/) (2024)

## Abstract (arXiv)

We demonstrate a backdoor attack on a deep neural network used for regression. The backdoor attack is localized based on training-set data poisoning wherein the mislabeled samples are surrounded by correctly labeled ones. We demonstrate how such localization is necessary for attack success. We also study the performance of a backdoor defense using gradient-based discovery of local error maximizers. Local error maximizers which are associated with significant (interpolation) error, and are proximal to many training samples, are suspicious. This method is also used to accurately train for deep regression in the first place by active (deep) learning leveraging an "oracle" capable of providing real-valued supervision (a regression target) for samples. Such oracles, including traditional numerical solvers of PDEs or SDEs using finite difference or Monte Carlo approximations, are far more computationally costly compared to deep regression.