mlsanityData to 14 Oct 2026

Detecting Backdoor Attacks Against Point Cloud Classifiers

arXiv 2110.10354 ↗First posted 20 Oct 2021cs.CR cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a source class is embedded with the backdoor pattern (BP). Recently, the first BA against point cloud (PC) classifiers was proposed, creating new threats to many important applications including autonomous driving. Such PC BAs are not detectable by existing BA defenses due to their special BP embedding mechanism. In this paper, we propose a reverse-engineering defense that infers whether a PC classifier is backdoor attacked, without access to its training set or to any clean classifiers for reference. The effectiveness of our defense is demonstrated on the benchmark ModeNet40 dataset for PCs.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 20 Oct 2021.

Builds on

19 of 26 references.

References · 19

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  6. 2018Spectral Signatures in Backdoor Attackscited by 484
  7. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  8. 2020Backdoor Learning: A Surveycited by 426
  9. 2018Generating 3D Adversarial Point Cloudscited by 144
  10. 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 122
  11. 2020Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Casescited by 95
  12. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
7 more
  1. 2021Black-box Detection of Backdoor Attacks with Limited Information and Datacited by 73
  2. 20203D Point Cloud Processing and Learning for Autonomous Drivingcited by 68
  3. 2021A Backdoor Attack against 3D Point Cloud Classifierscited by 53
  4. 2018Local Descriptor for Robust Place Recognition using LiDAR Intensitycited by 19
  5. 2019Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attackscited by 11
  6. 2020L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Setcited by 6
  7. 2019Revealing Perceptible Backdoors, without the Training Set, via the Maximum Achievable Misclassification Fraction Statisticcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 4.

10 papers.

  1. 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Modelscited by 80
  2. 2022MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statisticcited by 55
  3. 2024Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Modelscited by 33
  4. 2022Imperceptible and Robust Backdoor Attack in 3D Point Cloudcited by 25
  5. 2023UMD: Unsupervised Model Detection for X2X Backdoor Attackscited by 18
  6. 2023CBD: A Certified Backdoor Detector Based on Local Dominant Probabilitycited by 13
  7. 2022Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shapecited by 4
  8. 2024Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairnesscited by 3
  9. 2023Backdoor Mitigation by Correcting the Distribution of Neural Activationscited by 1
  10. 2024CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Predictioncited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2022Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios
  2. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloud
  3. 2021Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks
  4. 2022Detecting Backdoors in Deep Text Classifiers
  5. 2025DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
  6. 2021Anti-Backdoor Learning: Training Clean Models on Poisoned Data
  7. 2022Untargeted Backdoor Attack against Object Detection
  8. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences