mlsanityData to 7 Oct 2026

HoneyModels: Machine Learning Honeypots

arXiv 2202.10309 ↗First posted 21 Feb 2022cs.CR cs.AIcited by 0

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Machine Learning is becoming a pivotal aspect of many systems today, offering newfound performance on classification and prediction tasks, but this rapid integration also comes with new unforeseen vulnerabilities. To harden these systems the ever-growing field of Adversarial Machine Learning has proposed new attack and defense mechanisms. However, a great asymmetry exists as these defensive methods can only provide security to certain models and lack scalability, computational efficiency, and practicality due to overly restrictive constraints. Moreover, newly introduced attacks can easily bypass defensive strategies by making subtle alterations. In this paper, we study an alternate approach inspired by honeypots to detect adversaries. Our approach yields learned models with an embedded watermark. When an adversary initiates an interaction with our model, attacks are encouraged to add this predetermined watermark stimulating detection of adversarial examples. We show that HoneyModels can reveal 69.5% of adversaries attempting to attack a Neural Network while preserving the original functionality of the model. HoneyModels offer an alternate direction to secure Machine Learning that slightly affects the accuracy while encouraging the creation of watermarked adversarial samples detectable by the HoneyModel but indistinguishable from others for the adversary.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 25 of its 35 references that are in the map. First posted on arXiv 21 Feb 2022.

Builds on

25 of 35 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  9. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  10. 2016End to End Learning for Self-Driving Carscited by 1,000
  11. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  12. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
13 more
  1. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  2. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  3. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  4. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  5. 2018Certified Defenses against Adversarial Examplescited by 305
  6. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  7. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  8. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  9. 2017Adversarial and Clean Data Are Not Twinscited by 52
  10. 2017Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reductioncited by 49
  11. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  12. 2019Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networkscited by 40
  13. 2018Bypassing Feature Squeezing by Increasing Adversary Strengthcited by 8

Built on by

Not cited yet.