https://cis.temple.edu/~jiewu/research/publications/Publication_files/FedHAN.pdf
1 Introduction Federated learning (FL) [Koneˇcn ́y et al., 2017], a widely-used framework for distributed machine learning, is a signif-icant research focus. Most FL algorithms, such as the clas-sic FedAvg, fall into Synchronous Federated Learning (SFL). They require the server to wait for all selected clients’ lo-cal training and uploads before aggregating updates, and as-sume uniform ...
https://www.temple.edu/academics/degree-programs/information-technology-auditing-cyber-security-ms-bu-itac-ms
Prepare for a career in cyber security, IT risk management or information systems auditing in the business and critical infrastructure sectors.
https://law.temple.edu/aer/2023/05/15/evidence-advocacy-and-carroll-v-trump/
A jury of nine spoke with one voice. Donald Trump sexually assaulted a woman, brazenly, in a high-end department store, lied about it, and maliciously defamed his victim. To put it mildly, Mr. Trump was likely not the easiest client to represent, and his cause not the easiest to defend. But the case warrants a post-mortem to assess the tools of Evidence law that may have contributed to the ...
https://cis.temple.edu/~tug29203/18spring-3329/reading/Lab_7_Solutions.pdf
The answers below are based on the trace file tcp-ethereal-trace-1 in in
https://sites.temple.edu/ticlj/files/2017/02/30.1.Meier-TICLJ.pdf
Humanity by Human Rights Watch, lethal autonomous weapons systems (LAWS) have become an issue of national and international attention. With almost daily articles and commentary, including letters by notable scientists, debating the advantages and disadvantages of developing and fielding these systems, the public has become generally more aware of the issues related to autonomy, but it has ...
https://cis.temple.edu/~ingargio/cis587/readings/wumpus.shtml
A variety of "worlds" are being used as examples for Knowledge Representation, Reasoning, and Planning. Among them the Vacuum World, the Block World, and the Wumpus World. We will examine the Wumpus World and in this context introduce the Situation Calculus, the Frame Problem, and a variety of axioms.
https://news.temple.edu/nutshell/2023-03-20/what-do-you-meme-you-can-get-sued-social-post
Laney Griner, the mother of the child who became known as Success Kid and the person who snapped the iconic photo back in 2007, also filed another lawsuit against a fireworks company that used the image of her son to advertise one of its products. The fireworks company settled with Griner for an unspecified amount.
https://sites.temple.edu/ticlj/files/2020/05/34.1_Article-D-Final-Format.pdf
World leaders and human rights groups have criticized the ICC as expensive and ineffective. This critique is essentially an attack on the court’s legitimacy. This Note argues that Bemba’s acquittal only serves to weaken that legitimacy. Beginning with an analysis of the majority and minority opinions, it then discusses how the decision will impact the ICC’s legitimacy by imposing ...
https://cis.temple.edu/~wu/research/publications/Publication_files/J-CT-2024-Balancing%20Privacy%20and%20Accuracy%20using%20Siginificant%20Gradient%20Protection%20in%20Federated%20Learning.pdf
Abstract—Previous state-of-the-art studies have demonstrated that adversaries can access sensitive user data by membership inference attacks (MIAs) in Federated Learning (FL). Intro-ducing differential privacy (DP) into the FL framework is an effective way to enhance the privacy of FL. Nevertheless, in differentially private federated learning (DP-FL), local gradients become excessively ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/Distributed_Deep_Multi-Agent_Reinforcement_Learning_for_Cooperative_Edge_Caching_in_Internet-of-Vehicles.pdf
Abstract—Edge caching is a promising approach to reduce duplicate content transmission in Internet-of-Vehicles (IoVs). Sev-eral Reinforcement Learning (RL) based edge caching methods have been proposed to improve the resource utilization and reduce the backhaul trafic load. However, they only obtain the local sub-optimal solution, as they neglect the influence from environments by other ...