mlsanityData to 14 Oct 2026

RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

arXiv 2208.10608 ↗First posted 22 Aug 2022cs.CR cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed DNNs, which are widely used in the practical applications, is little exploited yet. In this paper, we propose to study and develop Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC). By performing systematic analysis and exploration on the important design knobs, we propose a framework that can learn the proper trigger patterns, model parameters and pruning masks in an efficient way. Thereby achieving high trigger stealthiness, high attack success rate and high model efficiency simultaneously. Extensive evaluations across different datasets, including the test against the state-of-the-art defense mechanisms, demonstrate the high robustness, stealthiness and model efficiency of RIBAC. Code is available at https://github.com/huyvnphan/ECCV2022-RIBAC

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 33 of its 45 references that are in the map. First posted on arXiv 22 Aug 2022.

Builds on

33 of 45 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  9. 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
  10. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  11. 2018Spectral Signatures in Backdoor Attackscited by 484
  12. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 459
21 more
  1. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 456
  2. 2019Hidden Trigger Backdoor Attackscited by 371
  3. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  4. 2019What's Hidden in a Randomly Weighted Neural Network?cited by 237
  5. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 235
  6. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 161
  7. 2017Neural Trojanscited by 153
  8. 2020Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustnesscited by 132
  9. 2015Accelerating Very Deep Convolutional Networks for Classification and Detectioncited by 109
  10. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  11. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
  12. 2020Rethinking the Trigger of Backdoor Attackcited by 77
  13. 2021Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Frameworkcited by 52
  14. 2020Enabling Fast and Universal Audio Adversarial Attack Using Generative Modelcited by 32
  15. 2020Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systemscited by 26
  16. 2019Towards Compact and Robust Deep Neural Networkscited by 23
  17. 2021Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomescited by 19
  18. 2020Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Modelscited by 18
  19. 2021Stealthy Backdoors as Compression Artifactscited by 18
  20. 2021Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structurecited by 8
  21. 2019CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generatorcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 2.

4 papers.

  1. 2022CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustnesscited by 4
  2. 2023Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attackscited by 2
  3. 2025SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systemscited by 0
  4. 2025Quantization Blindspots: How Model Compression Breaks Backdoor Defensescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Backdoor Attack with Sparse and Invisible Trigger
  2. 2022Imperceptible Backdoor Attack: From Input Space to Feature Representation
  3. 2022BackdoorBench: A Comprehensive Benchmark of Backdoor Learning
  4. 2024BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
  5. 2024An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers
  6. 2024BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
  7. 2023BackdoorBox: A Python Toolbox for Backdoor Learning
  8. 2024A Practical Trigger-Free Backdoor Attack on Neural Networks ↗