Sökning: "Adversarial Attacks"

Visar resultat 1 - 5 av 35 uppsatser innehållade orden Adversarial Attacks.

1. 1. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models

   Master-uppsats, Umeå universitet/Institutionen för datavetenskap

   Författare :Sofia Leksell; [2024]
   Nyckelord :Federated Learning; Adversarial Attacks; Regression; Classification;

   Sammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving  a noticeable gap in FL research specifically for regression models. LÄS MER

3. 2. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models

   Master-uppsats, Umeå universitet/Institutionen för tillämpad fysik och elektronik

   Författare :Sofia Leksell; [2024]
   Nyckelord :Federated Learning; Adversarial Attacks; Regression; Classification;

   Sammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving  a noticeable gap in FL research specifically for regression models. LÄS MER

4. 3. Adversarial robustness of STDP-trained spiking neural networks

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Karl Lindblad; Axel Nilsson; [2023]
   Nyckelord :;

   Sammanfattning : Adversarial attacks on machine learning models are designed to elicit the wrong behavior from the model. One such attack on image classifiers are maliciously crafted inputs that, to the human eye, look untampered with but have been carefully altered to cause misclassification. LÄS MER

5. 4. Exploring GANs to generate attack-variations in IoT networks

   Kandidat-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Gustaf Bennmarker; [2023]
   Nyckelord :;

   Sammanfattning : Data driven IDS development requires a vast amount of data to be effective against future attacks and a big problem is the lack of available data. This thesis explores the use of GANs (Generative adversarial networks) in generating attack data that can be used as apart of a training set for an IDS to improve the robustness against adversarial attacks. LÄS MER

7. 5. Adversarial Machine (Deep) Learning-basedRobustification in 5G Networks

   Master-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Författare :Mirjalol Aminov; [2023]
   Nyckelord :5G; Network Slicing; Adversarial Machine Learning; Machine Learning; Deep Learning;

   Sammanfattning :  A significant development in wireless communication and artificial intelligence has been made possible by the combination of 5G networks with deep learning methods. This paper explores the complex interactions between these areas, concentrating on the dangers that adversarial attacks represent in the context of 5G network slicing. LÄS MER