mlsanityData to 7 Oct 2026

One-pixel Signature: Characterizing CNN Models for Backdoor Detection

arXiv 2008.07711 ↗First posted 18 Aug 2020cs.CV cs.CR cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

We tackle the convolution neural networks (CNNs) backdoor detection problem by proposing a new representation called one-pixel signature. Our task is to detect/classify if a CNN model has been maliciously inserted with an unknown Trojan trigger or not. Here, each CNN model is associated with a signature that is created by generating, pixel-by-pixel, an adversarial value that is the result of the largest change to the class prediction. The one-pixel signature is agnostic to the design choice of CNN architectures, and how they were trained. It can be computed efficiently for a black-box CNN model without accessing the network parameters. Our proposed one-pixel signature demonstrates a substantial improvement (by around 30% in the absolute detection accuracy) over the existing competing methods for backdoored CNN detection/classification. One-pixel signature is a general representation that can be used to characterize CNN models beyond backdoor detection.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 11; 2023: 7; 2024: 5; 2025: 3; 2026: 1.

34 papers.

Sort:

By area:

  1. 2021Backdoor Scanning for Deep Neural Networks through K-Arm Optimizationcited by 96
  2. 2022Backdoor Defense with Machine Unlearningcited by 61
  3. 2022Fine-mixing: Mitigating Backdoors in Fine-tuned Language Modelscited by 50
  4. 2022BadDet: Backdoor Attacks on Object Detectioncited by 45
  5. 2022Training with More Confidence: Mitigating Injected and Natural Backdoors During Trainingcited by 38
  6. 2022FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learningcited by 37
  7. 2021How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Datacited by 22
  8. 2023Defending Against Patch-based Backdoor Attacks on Self-Supervised Learningcited by 19
  9. 2021Backdoor Attack through Frequency Domaincited by 18
  10. 2022A Survey of Neural Trojan Attacks and Defenses in Deep Learningcited by 17
  11. 2023BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defensecited by 15
  12. 2022Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifierscited by 14
22 more
  1. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  2. 2023A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectivescited by 13
  3. 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregationcited by 8
  4. 2023Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detectioncited by 6
  5. 2023Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Datacited by 6
  6. 2021EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetrycited by 5
  7. 2021MISA: Online Defense of Trojaned Models using Misattributionscited by 4
  8. 2021Reachability Analysis of Convolutional Neural Networkscited by 4
  9. 2022DECK: Model Hardening for Defending Pervasive Backdoorscited by 4
  10. 2026Attribution-Guided Model Rectification of Unreliable Neural Network Behaviorscited by 3
  11. 2022PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networkscited by 2
  12. 2021A General Framework for Defending Against Backdoor Attacks via Influence Graphcited by 1
  13. 2024Invisible Backdoor Attack Through Singular Value Decompositioncited by 1
  14. 2024Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Modelscited by 1
  15. 2025FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clientscited by 1
  16. 2022gSuite: A Flexible and Framework Independent Benchmark Suite for Graph Neural Network Inference on GPUscited by 0
  17. 2023AGNES: Abstraction-guided Framework for Deep Neural Networks Securitycited by 0
  18. 2024Detecting Face Synthesis Using a Concealed Fusion Modelcited by 0
  19. 2024Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attackscited by 0
  20. 2024Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagerycited by 0
  21. 2025CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-Worldcited by 0
  22. 2025ArcGen: Generalizing Neural Backdoor Detection Across Diverse Architecturescited by 0