mlsanityData to 7 Oct 2026

Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks

arXiv 1905.12032 ↗First posted 28 May 2019cs.LG cs.CR cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters. We apply ADMM (alternating direction method of multipliers) for solving the optimization problem of the fault sneaking attack with two constraints: 1) the classification of the other images should be unchanged and 2) the parameter modifications should be minimized. Specifically, the first constraint requires us not only to inject designated faults (misclassifications), but also to hide the faults for stealthy or sneaking considerations by maintaining model accuracy. The second constraint requires us to minimize the parameter modifications (using L0 norm to measure the number of modifications and L2 norm to measure the magnitude of modifications). Comprehensive experimental evaluation demonstrates that the proposed framework can inject multiple sneaking faults without losing the overall test accuracy performance.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 4; 2023: 5; 2024: 3; 2025: 1; 2026: 1.

25 papers.

Sort:

By area:

  1. 2021Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bitscited by 49
  2. 2021Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networkscited by 33
  3. 2021Formalizing Generalization and Robustness of Neural Networks to Weight Perturbationscited by 22
  4. 2022Hardly Perceptible Trojan Attack against Neural Networks with Bit Flipscited by 21
  5. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  6. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  7. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Surveycited by 15
  8. 2023One-bit Flip is All You Need: When Bit-flip Attack Meets Model Trainingcited by 14
  9. 2022Versatile Weight Attack via Flipping Limited Bitscited by 13
  10. 2021RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracycited by 11
  11. 2021DeepPoison: Feature Transfer Based Stealthy Poisoning Attackcited by 8
  12. 2021FooBaR: Fault Fooling Backdoor Attack on Neural Network Trainingcited by 6
13 more
  1. 2022Adversarial Parameter Attack on Deep Neural Networkscited by 6
  2. 2021Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attackscited by 4
  3. 2021ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attackcited by 3
  4. 2021Non-Singular Adversarial Robustness of Neural Networkscited by 2
  5. 2024On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMscited by 2
  6. 2021BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networkscited by 1
  7. 2023Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing Systemcited by 1
  8. 2023An Incremental Gray-box Physical Adversarial Attack on Neural Network Trainingcited by 1
  9. 2023Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignmentcited by 1
  10. 2025SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Modelscited by 1
  11. 2021Attacking Deep Learning AI Hardware with Universal Adversarial Perturbationcited by 0
  12. 2024Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learningcited by 0
  13. 2026Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attackscited by 0