Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Hossen, Md. Imran"'
Autor:
Hossen, Md Imran, Hei, Xiali
The advent of instruction-tuned Large Language Models designed for coding tasks (Code LLMs) has transformed software engineering practices. However, their robustness against various input challenges remains a critical concern. This study introduces D
Externí odkaz:
http://arxiv.org/abs/2411.19508
Instruction-tuned Code Large Language Models (Code LLMs) are increasingly utilized as AI coding assistants and integrated into various applications. However, the cybersecurity vulnerabilities and implications arising from the widespread integration o
Externí odkaz:
http://arxiv.org/abs/2404.18567
Autor:
Ji, Xu, Zhang, Jianyi, Zhou, Ziyin, Zhao, Zhangchi, Qiao, Qianqian, Han, Kaiying, Hossen, Md Imran, Hei, Xiali
Ensuring the resilience of Large Language Models (LLMs) against malicious exploitation is paramount, with recent focus on mitigating offensive responses. Yet, the understanding of cant or dark jargon remains unexplored. This paper introduces a domain
Externí odkaz:
http://arxiv.org/abs/2405.00718
Rice disease classification is a critical task in agricultural research, and in this study, we rigorously evaluate the impact of integrating feature extraction methodologies within pre-trained convolutional neural networks (CNNs). Initial investigati
Externí odkaz:
http://arxiv.org/abs/2405.00025
The primary goal of this project is to develop privacy-preserving machine learning model training techniques for fNIRS data. This project will build a local model in a centralized setting with both differential privacy (DP) and certified robustness.
Externí odkaz:
http://arxiv.org/abs/2401.00973
DP-SGD has emerged as a popular method to protect personally identifiable information in deep learning applications. Unfortunately, DP-SGD's per-sample gradient clipping and uniform noise addition during training can significantly degrade model utili
Externí odkaz:
http://arxiv.org/abs/2312.02400
Autor:
Hossen, Md Imran, Hei, Xiali
CAPTCHAs are designed to prevent malicious bot programs from abusing websites. Most online service providers deploy audio CAPTCHAs as an alternative to text and image CAPTCHAs for visually impaired users. However, prior research investigating the sec
Externí odkaz:
http://arxiv.org/abs/2203.02735
Autor:
Hossen, Md Imran, Islam, Ashraful, Anowar, Farzana, Ahmed, Eshtiak, Rahman, Mohammad Masudur, Xiali, Hei
Due to the variety of cyber-attacks or threats, the cybersecurity community enhances the traditional security control mechanisms to an advanced level so that automated tools can encounter potential security threats. Very recently, Cyber Threat Intell
Externí odkaz:
http://arxiv.org/abs/2108.06862
Autor:
Hossen, Md Imran, Hei, Xiali
CAPTCHAs are a defense mechanism to prevent malicious bot programs from abusing websites on the Internet. hCaptcha is a relatively new but emerging image CAPTCHA service. This paper presents an automated system that can break hCaptcha challenges with
Externí odkaz:
http://arxiv.org/abs/2104.04683
Previous work showed that reCAPTCHA v2's image challenges could be solved by automated programs armed with Deep Neural Network (DNN) image classifiers and vision APIs provided by off-the-shelf image recognition services. In response to emerging threa
Externí odkaz:
http://arxiv.org/abs/2104.03366