Výsledky vyhledávání

Report

Legal Prompting: Teaching a Language Model to Think Like a Lawyer

Autor: Yu, Fangyi, Quartey, Lee, Schilder, Frank

Large language models that are capable of zero or few-shot prompting approaches have given rise to the new research area of prompt engineering. Recent advances showed that for example Chain-of-Thought (CoT) prompts can improve arithmetic or common se

Externí odkaz: http://arxiv.org/abs/2212.01326

Zobrazit plný text záznamu

Report

On Deep Learning in Password Guessing, a Survey

Autor: Yu, Fangyi

The security of passwords is dependent on a thorough understanding of the strategies used by attackers. Unfortunately, real-world adversaries use pragmatic guessing tactics like dictionary attacks, which are difficult to simulate in password security

Externí odkaz: http://arxiv.org/abs/2208.10413

Zobrazit plný text záznamu

Report

Targeted Honeyword Generation with Language Models

Autor: Yu, Fangyi, Martin, Miguel Vargas

Honeywords are fictitious passwords inserted into databases in order to identify password breaches. The major difficulty is how to produce honeywords that are difficult to distinguish from real passwords. Although the generation of honeywords has bee

Externí odkaz: http://arxiv.org/abs/2208.06946

Zobrazit plný text záznamu

Report

GNPassGAN: Improved Generative Adversarial Networks For Trawling Offline Password Guessing

Autor: Yu, Fangyi, Martin, Miguel Vargas

Publikováno v: 2022 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), 2022, pp. 10-18

The security of passwords depends on a thorough understanding of the strategies used by attackers. Unfortunately, real-world adversaries use pragmatic guessing tactics like dictionary attacks, which are difficult to simulate in password security rese

Externí odkaz: http://arxiv.org/abs/2208.06943

Zobrazit plný text záznamu