Sökning: "defending"
Visar resultat 1 - 5 av 194 uppsatser innehållade ordet defending.
1. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : 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
2. In Defense of Consuming Animal Products : How Human Suffering Can Justify the Consumption of Animal Products in Developed Countries
Kandidat-uppsats, Uppsala universitet/Filosofiska institutionenSammanfattning : Within the area of animal ethics, there has been ongoing discussion around whether people in developed countries are justified in consuming animal based products or not, some argue that we are, and some argue that we aren't. In this paper I present a kind of middle-way position in response to the ongoing discussion, in which I argue that a decent chunk of a population in developed countries are justified in consuming certain animal products, but only so far as the exclusion of these animal based products would cause harm to the boycotter. LÄS MER
3. Stopp, samhällets kropp (?)
L2-uppsats, Lunds universitet/Statsvetenskapliga institutionenSammanfattning : The medial coverage as well as political interest of criminal rates in Sweden has increased over the years, especially regarding organized crime. Therefore this study aims to investigate how the discourse within criminal politics in Sweden has evolved during the last two terms. LÄS MER
4. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models
Master-uppsats, Umeå universitet/Institutionen för tillämpad fysik och elektronikSammanfattning : 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
5. Literature review on trustworthiness of Signature-Based and Anomaly detection in Wireless Networks
Kandidat-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : The internet has become an essential part of most people's daily lives in recent years, and as more devices connect to the internet, the risk of cyber threats increases dramatically. As malware becomes more sophisticated, traditional security prevention measures are becoming less effective at defending from cyber attacks. LÄS MER