CorrGAN: Input Transformation Technique Against Natural Corruptions
Because of the increasing accuracy of Deep Neural Networks (DNNs) on different tasks, a lot of real times systems are utilizing DNNs. These DNNs are vulnerable to adversarial perturbations and corruptions. Specifically, natural corruptions like fog, blur, contrast etc can affect the prediction of DNN in an autonomous vehicle. In real time, these corruptions are needed to be detected and also the corrupted inputs are needed to be de-noised to be predicted correctly. In this work, we propose CorrGAN approach, which can generate benign input when a corrupted input is provided. In this framework, we train Generative Adversarial Network (GAN) with novel intermediate output-based loss function. The GAN can denoise the corrupted input and generate benign input. Through experimentation, we show that up to 75.2% of the corrupted misclassified inputs can be classified correctly by DNN using CorrGAN.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkSimilar Papers 제목 키워드 기반
Certifying Model Accuracy under Distribution Shifts
Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this work, we present provable robustness gu…
modelAugmenting Model Robustness with Transformation-Invariant Attacks
The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensiti…
Image CroppingmodelTranslationTowards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing
In this paper, we propose shifting the focus of robustness evaluation for Neural Program Repair (NPR) techniques toward naturally-occurring data transformations. To accomplish this, we first examine the naturalness of se…
Program RepairWatermarks for Embeddings-as-a-Service Large Language Models
Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs, businesses have started to provide Embeddings-as-a-Service (EaaS), offering f…
Natural Language UnderstandingDECK: Model Hardening for Defending Pervasive Backdoors
Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditi…
Decodermodel