mlsanityData to 7 Oct 2026

Backdoor Attack and Defense for Deep Regression

arXiv 2109.02381 ↗First posted 6 Sep 2021cs.LG cs.CRcited by 6

Not on the map. Why?

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

12 of 22 references.

References · 12

  1. 2016An overview of gradient descent optimization algorithmscited by 1,021
  2. 2020A Survey of Deep Active Learningcited by 547
  3. 2018A Comprehensive Analysis of Deep Regressioncited by 48
  4. 2019Neural networks for option pricing and hedging: a literature reviewcited by 38
  5. 2018Active Learning for Regression Using Greedy Samplingcited by 26
  6. 2018Dropout-based Active Learning for Regressioncited by 24
  7. 2019Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attackscited by 11
  8. 2020Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansingcited by 11
  9. 2019Detection of Backdoors in Trained Classifiers Without Access to the Training Setcited by 7
  10. 2017Adversarial Learning: A Critical Review and Active Learning Studycited by 6
  11. 2018Deeply Learning Derivativescited by 3
  12. 2021Robust and Active Learning for Deep Neural Network Regressioncited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 2; 2024: 3.

6 papers.

  1. 2021Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networkscited by 10
  2. 2024BadGD: A unified data-centric framework to identify gradient descent vulnerabilitiescited by 5
  3. 2023Temporal-Distributed Backdoor Attack Against Video Based Action Recognitioncited by 3
  4. 2024Defending Deep Regression Models against Backdoor Attackscited by 3
  5. 2023Backdoor Mitigation by Correcting the Distribution of Neural Activationscited by 1
  6. 2024Poisoning Attacks on Federated Learning for Autonomous Drivingcited by 0