mlsanityData to 14 Oct 2026

Exploring Secure Machine Learning Through Payload Injection and FGSM Attacks on ResNet-50

arXiv 2501.02147 ↗First posted 4 Jan 2025cs.CR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper investigates the resilience of a ResNet-50 image classification model under two prominent security threats: Fast Gradient Sign Method (FGSM) adversarial attacks and malicious payload injection. Initially, the model attains a 53.33% accuracy on clean images. When subjected to FGSM perturbations, its overall accuracy remains unchanged; however, the model's confidence in incorrect predictions notably increases. Concurrently, a payload injection scheme is successfully executed in 93.33% of the tested samples, revealing how stealthy attacks can manipulate model predictions without degrading visual quality. These findings underscore the vulnerability of even high-performing neural networks and highlight the urgency of developing more robust defense mechanisms for security-critical applications.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 12 of its 20 references that are in the map. First posted on arXiv 4 Jan 2025.

Builds on

12 of 20 references.

References · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  8. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  9. 2016Universal adversarial perturbationscited by 784
  10. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  11. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  12. 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 54

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directionscited by 8
  2. 2026Chunking, Retrieval, and Re-ranking: An Empirical Evaluation of RAG Architectures for Policy Document Question Answeringcited by 2