paper-with-me

홈 › Papers

Exploring the role of Input and Output Layers of a Deep Neural Network in Adversarial Defense

2020-06-02 · Jay N. Paranjape, Rahul Kumar Dubey, Vijendran V Gopalan

Deep neural networks are learning models having achieved state of the art performance in many fields like prediction, computer vision, language processing and so on. However, it has been shown that certain inputs exist which would not trick a human normally, but may mislead the model completely. These inputs are known as adversarial inputs. These inputs pose a high security threat when such models are used in real world applications. In this work, we have analyzed the resistance of three different classes of fully connected dense networks against the rarely tested non-gradient based adversarial attacks. These classes are created by manipulating the input and output layers. We have proven empirically that owing to certain characteristics of the network, they provide a high robustness against these attacks, and can be used in fine tuning other models to increase defense against adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2006.01408

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Defense

Similar Papers 제목 키워드 기반

Exploring Layerwise Adversarial Robustness Through the Lens of t-SNE

2024-06-20 · Inês Valentim, Nuno Antunes, Nuno Lourenço

Adversarial examples, designed to trick Artificial Neural Networks (ANNs) into producing wrong outputs, highlight vulnerabilities in these models. Exploring these weaknesses is crucial for developing defenses, and so, we…

Adversarial Robustness

Contrasting Adversarial Perturbations: The Space of Harmless Perturbations

2024-02-03 · Lu Chen, Shaofeng Li, Benhao Huang, Fan Yang 외

Existing works have extensively studied adversarial examples, which are minimal perturbations that can mislead the output of deep neural networks (DNNs) while remaining imperceptible to humans. However, in this work, we …

Privacy Preserving

DE-PACRR: Exploring Layers Inside the PACRR Model

2017-06-27 · Andrew Yates, Kai Hui

Recent neural IR models have demonstrated deep learning's utility in ad-hoc information retrieval. However, deep models have a reputation for being black boxes, and the roles of a neural IR model's components may not be …

Ad-Hoc Information RetrievalInformation RetrievalmodelRetrieval

Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models

2019-05-13 · Mayank Singh, Abhishek Sinha, Nupur Kumari, Harshitha Machiraju 외

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adver…

Adversarial Attack

Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems

2025-10-22 · Mohamed ElShehaby, Ashraf Matrawy arxiv

Adversarial attacks pose significant challenges to Machine Learning (ML) systems and especially Deep Neural Networks (DNNs) by subtly manipulating inputs to induce incorrect predictions. This paper investigates whether i…

Network Intrusion DetectionAdversarial RobustnessAdversarial Attack