Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessModel CompressionQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Attacks on Machine Learning in Embedded and IoT Platforms
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 CompressionBenchmarking Adversarial Robustness of Compressed Deep Learning Models
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 CompressionHardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning
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 RobustnessQuantizationEGC2: Enhanced Graph Classification with Easy Graph Compression
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 ClassificationExploring adversarial robustness of JPEG AI: methodology, comparison and new methods
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