mlsanityData to 7 Oct 2026

Adversarial Reprogramming of Neural Networks

arXiv 1806.11146 ↗First posted 28 Jun 2018cs.LG cs.CR cs.CVcited by 115

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are susceptible to adversarial attacks. In computer vision, well-crafted perturbations to images can cause neural networks to make mistakes such as confusing a cat with a computer. Previous adversarial attacks have been designed to degrade performance of models or cause machine learning models to produce specific outputs chosen ahead of time by the attacker. We introduce attacks that instead em reprogram the target model to perform a task chosen by the attacker---without the attacker needing to specify or compute the desired output for each test-time input. This attack finds a single adversarial perturbation, that can be added to all test-time inputs to a machine learning model in order to cause the model to perform a task chosen by the adversary---even if the model was not trained to do this task. These perturbations can thus be considered a program for the new task. We demonstrate adversarial reprogramming on six ImageNet classification models, repurposing these models to perform a counting task, as well as classification tasks: classification of MNIST and CIFAR-10 examples presented as inputs to the ImageNet model.

Key facts. Cited by 115 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 18; 2023: 40; 2024: 25; 2025: 16; 2026: 8.

115 papers.

Sort:

By area:

  1. 2022Visual Prompt Tuningcited by 1,674
  2. 2022Exploring Visual Prompts for Adapting Large-Scale Modelscited by 271
  3. 2021WARP: Word-level Adversarial ReProgrammingcited by 220
  4. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  5. 2023The Expressive Power of Low-Rank Adaptationcited by 100
  6. 2021Voice2Series: Reprogramming Acoustic Models for Time Series Classificationcited by 91
  7. 2022Understanding and Improving Visual Prompting: A Label-Mapping Perspectivecited by 86
  8. 2023BlackVIP: Black-Box Visual Prompting for Robust Transfer Learningcited by 70
  9. 2022Model Reprogramming: Resource-Efficient Cross-Domain Machine Learningcited by 64
  10. 2022Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNetscited by 62
  11. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  12. 2024Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Reviewcited by 50
38 more
  1. 2022Unleashing the Power of Visual Prompting At the Pixel Levelcited by 37
  2. 2021Cross-modal Adversarial Reprogrammingcited by 34
  3. 2023The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Modelscited by 34
  4. 2025Shared Global and Local Geometry of Language Model Embeddingscited by 34
  5. 2022Fairness Reprogrammingcited by 33
  6. 2022Visual Prompting for Adversarial Robustnesscited by 33
  7. 2023Instruct Me More! Random Prompting for Visual In-Context Learningcited by 30
  8. 2024Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detectioncited by 30
  9. 2023AutoVP: An Automated Visual Prompting Framework and Benchmarkcited by 29
  10. 2022Watermarking for Out-of-distribution Detectioncited by 28
  11. 2023From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognitioncited by 23
  12. 2023Deep Graph Reprogrammingcited by 22
  13. 2023SpeechGen: Unlocking the Generative Power of Speech Language Models with Promptscited by 21
  14. 2022Reprogramming Pretrained Language Models for Antibody Sequence Infillingcited by 20
  15. 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogrammingcited by 20
  16. 2022SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Taskscited by 19
  17. 2023Text-Visual Prompting for Efficient 2D Temporal Video Groundingcited by 18
  18. 2022Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogrammingcited by 17
  19. 2023Convolutional Visual Prompt for Robust Visual Perceptioncited by 17
  20. 2023Exploring the Benefits of Visual Prompting in Differential Privacycited by 17
  21. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  22. 2024Algorithmic Capabilities of Random Transformerscited by 17
  23. 2023Visual Prompt Based Personalized Federated Learningcited by 16
  24. 2024Sample-specific Masks for Visual Reprogramming-based Promptingcited by 16
  25. 2024Exploring the Transferability of Visual Prompting for Multimodal Large Language Modelscited by 15
  26. 2021Get a Model! Model Hijacking Attack Against Machine Learning Modelscited by 13
  27. 2023Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognitioncited by 13
  28. 2023Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?cited by 13
  29. 2024CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuningcited by 13
  30. 2023Reprogramming Pretrained Language Models for Protein Sequence Representation Learningcited by 12
  31. 2024SpeechPrompt: Prompting Speech Language Models for Speech Processing Taskscited by 12
  32. 2024Bayesian-guided Label Mapping for Visual Reprogrammingcited by 12
  33. 2023Two-in-One: A Model Hijacking Attack Against Text Generation Modelscited by 11
  34. 2023VPA: Fully Test-Time Visual Prompt Adaptationcited by 11
  35. 2023Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learningcited by 11
  36. 2022Adversarial Reprogramming Revisitedcited by 10
  37. 2022Prompt Generation Networks for Input-Space Adaptation of Frozen Vision Transformerscited by 8
  38. 2023A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-Trained General-Purpose Speech Modelcited by 8

50 most cited of 115 All 115 (JSON)