Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence

Svetlana Pavlitska, Hannes Grolig, J. Marius Zöllner
11/27/2023
cs.LGcs.CV

No confident code implementation found for this paper.

Abstract

Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the network while preserving its accuracy. Several recent studies have addressed the relationship between model compression and adversarial robustness, while some experiments have reported contradictory results. This work summarizes available evidence and discusses possible explanations for the observed effects.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency

91% match1 repo12024

On the Interaction of Compressibility and Adversarial Robustness

87% match1 repo12025

Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions

85% match2025

Feature compression is the root cause of adversarial fragility in neural network classifiers

85% match2024

Adversarial Attacks on Machine Learning in Embedded and IoT Platforms

85% match2023

Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models

84% match2024

Cite this paper

@article{pavlitska2023relationship,
  title  = {Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence},
  author = {Svetlana Pavlitska and Hannes Grolig and J. Marius Zöllner},
  year   = {2023},
  eprint = {2311.15782},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.15782v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.15782.svg)](https://codeofpaper.com/paper/2311.15782)

Discussion