mlsanityData to 14 Oct 2026

Interactive Simulations of Backdoors in Neural Networks

arXiv 2405.13217 ↗First posted 21 May 2024cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting undetectable backdoors under theoretical assumptions in the large AI model systems deployed in practice. Our approach is based on designing a web-based simulation playground that enables planting, activating, and defending cryptographic backdoors in neural networks (NN). Simulations of planting and activating backdoors are enabled for two scenarios: in the extension of NN model architecture to support digital signature verification and in the modified architectural block for non-linear operators. Simulations of backdoor defense against backdoors are available based on proximity analysis and provide a playground for a game of planting and defending against backdoors. The simulations are available at https://pages.nist.gov/nn-calculator

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 21 May 2024.

Builds on

17 of 29 references.

References · 17

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 308
  4. 2018Certified Defenses against Adversarial Examplescited by 306
  5. 2023BitNet: Scaling 1-bit Transformers for Large Language Modelscited by 189
  6. 2020Blind Backdoors in Deep Learning Modelscited by 182
  7. 2019TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systemscited by 122
  8. 2022Planting Undetectable Backdoors in Machine Learning Modelscited by 59
  9. 2018A Game-Based Approximate Verification of Deep Neural Networks with Provable Guaranteescited by 33
  10. 2021Quantization Backdoors to Deep Learning Commercial Frameworkscited by 29
  11. 2023ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigmscited by 29
  12. 2017Direct-Manipulation Visualization of Deep Networkscited by 28
5 more
  1. 2023A LLM Assisted Exploitation of AI-Guardiancited by 15
  2. 2024Architectural Neural Backdoors from First Principlescited by 11
  3. 2020Provably Robust Adversarial Examplescited by 8
  4. 2023A Survey of Data Security: Practices from Cybersecurity and Challenges of Machine Learningcited by 1
  5. 2024Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectorscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Cryptographic Backdoor for Neural Networks: Boon and Bane
  2. 2026Statistically Undetectable Backdoors in Deep Neural Networks
  3. 2022Verifying Neural Networks Against Backdoor Attacks
  4. 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
  5. 2024Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models
  6. 2022Architectural Backdoors in Neural Networks
  7. 2024Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
  8. 2026Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective