paper-with-me

홈 › Papers

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

2023-11-27 · Svetlana Pavlitska, Hannes Grolig, J. Marius Zöllner

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.

📄 PDF Abstract BibTeX arXiv:2311.15782

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessModel CompressionQuantization

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Attacks on Machine Learning in Embedded and IoT Platforms

2023-03-03 · Christian Westbrook, Sudeep Pasricha

Machine learning (ML) algorithms are increasingly being integrated into embedded and IoT systems that surround us, and they are vulnerable to adversarial attacks. The deployment of these ML algorithms on resource-limited…

Adversarial RobustnessModel Compression

Benchmarking Adversarial Robustness of Compressed Deep Learning Models

2023-08-16 · Brijesh Vora, Kartik Patwari, Syed Mahbub Hafiz, Zubair Shafiq 외

The increasing size of Deep Neural Networks (DNNs) poses a pressing need for model compression, particularly when employed on resource constrained devices. Concurrently, the susceptibility of DNNs to adversarial attacks …

Adversarial RobustnessBenchmarkingDeep LearningModel Compression

Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning

2022-06-15 · Jonah O'Brien Weiss, Tiago Alves, Sandip Kundu

The prevalence and success of Deep Neural Network (DNN) applications in recent years have motivated research on DNN compression, such as pruning and quantization. These techniques accelerate model inference, reduce power…

Adversarial RobustnessQuantization

EGC2: Enhanced Graph Classification with Easy Graph Compression

2021-07-16 · Jinyin Chen, Haiyang Xiong, Haibin Zhenga, Dunjie Zhang 외

Graph classification is crucial in network analyses. Networks face potential security threats, such as adversarial attacks. Some defense methods may trade off the algorithm complexity for robustness, such as adversarial …

ClassificationGraph Classification

Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods

2024-11-18 · Egor Kovalev, Georgii Bychkov, Khaled Abud, Aleksandr Gushchin 외

Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI - the first stan…

Adversarial RobustnessImage Compression