Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression
Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a common method to enhance model robustness. However, the improvement effect of adversarial training on model robustness is limited. In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models. Specifically, first, we propose a gradient regularization constraint for training robust teacher models. Subsequently, we design a knowledge distillation based strategy to generate a priori knowledge from the teacher model to the student model for guiding adversarial training. Experimental results show that our method improves the reconstruction quality by about 9dB when the Kodak dataset is elected as the backdoor attack object for psnr attack. Compared with Ma2023, our method has a 5dB higher PSNR output at high bitrate points.
Code (0)
등록된 구현이 없습니다.
Tasks
Backdoor AttackImage CompressionKnowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection
This paper introduces ROSAR, a novel framework enhancing the robustness of deep learning object detection models tailored for side-scan sonar (SSS) images, generated by autonomous underwater vehicles using sonar sensors.…
Knowledge Distillationobject-detectionObject DetectionImproving Adversarial Robustness Through Adaptive Learning-Driven Multi-Teacher Knowledge Distillation
Convolutional neural networks (CNNs) excel in computer vision but are susceptible to adversarial attacks, crafted perturbations designed to mislead predictions. Despite advances in adversarial training, a gap persists be…
Adversarial RobustnessKnowledge DistillationOnline Adversarial Knowledge Distillation for Graph Neural Networks
Knowledge distillation, a technique recently gaining popularity for enhancing model generalization in Convolutional Neural Networks (CNNs), operates under the assumption that both teacher and student models are trained o…
Knowledge DistillationEnhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation
Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on access to the original training set, which mi…
Knowledge DistillationDynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge
In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillatio…
Transfer Learning