Zobrazeno 1 - 10
of 216
pro vyhledávání: '"Hu, Hongxin"'
The vulnerability of machine learning models to Membership Inference Attacks (MIAs) has garnered considerable attention in recent years. These attacks determine whether a data sample belongs to the model's training set or not. Recent research has foc
Externí odkaz:
http://arxiv.org/abs/2409.00426
Timely and effective vulnerability patching is essential for cybersecurity defense, for which various approaches have been proposed yet still struggle to generate valid and correct patches for real-world vulnerabilities. In this paper, we leverage th
Externí odkaz:
http://arxiv.org/abs/2408.13597
Autor:
Okpala, Ebuka, Vishwamitra, Nishant, Guo, Keyan, Liao, Song, Cheng, Long, Hu, Hongxin, Wu, Yongkai, Yuan, Xiaohong, Wade, Jeannette, Khorsandroo, Sajad
Cyberharassment is a critical, socially relevant cybersecurity problem because of the adverse effects it can have on targeted groups or individuals. While progress has been made in understanding cyber-harassment, its detection, attacks on artificial
Externí odkaz:
http://arxiv.org/abs/2405.08125
Autor:
Xu, Xiaoyang, Yang, Mengda, Yi, Wenzhe, Li, Ziang, Wang, Juan, Hu, Hongxin, Zhuang, Yong, Liu, Yaxin
Split Learning (SL) is a distributed learning framework renowned for its privacy-preserving features and minimal computational requirements. Previous research consistently highlights the potential privacy breaches in SL systems by server adversaries
Externí odkaz:
http://arxiv.org/abs/2405.04115
The advancement in computing and hardware, like spatial computing and VR headsets (e.g., Apple's Vision Pro) [1], has boosted the popularity of social VR platforms (VRChat, Rec Room, Meta HorizonWorlds) [2, 3, 4]. Unlike traditional digital interacti
Externí odkaz:
http://arxiv.org/abs/2405.05928
Autor:
Guo, Keyan, Utkarsh, Ayush, Ding, Wenbo, Ondracek, Isabelle, Zhao, Ziming, Freeman, Guo, Vishwamitra, Nishant, Hu, Hongxin
Online user generated content games (UGCGs) are increasingly popular among children and adolescents for social interaction and more creative online entertainment. However, they pose a heightened risk of exposure to explicit content, raising growing c
Externí odkaz:
http://arxiv.org/abs/2403.18957
Security vulnerabilities are increasingly prevalent in modern software and they are widely consequential to our society. Various approaches to defending against these vulnerabilities have been proposed, among which those leveraging deep learning (DL)
Externí odkaz:
http://arxiv.org/abs/2402.17230
Autor:
Tan, Xi, Ma, Zheyuan, Pinto, Sandro, Guan, Le, Zhang, Ning, Xu, Jun, Lin, Zhiqiang, Hu, Hongxin, Zhao, Ziming
Arm Cortex-M processors are the most widely used 32-bit microcontrollers among embedded and Internet-of-Things devices. Despite the widespread usage, there has been little effort in summarizing their hardware security features, characterizing the lim
Externí odkaz:
http://arxiv.org/abs/2401.15289
Autor:
Guo, Keyan, Hu, Alexander, Mu, Jaden, Shi, Ziheng, Zhao, Ziming, Vishwamitra, Nishant, Hu, Hongxin
Hate speech has emerged as a major problem plaguing our social spaces today. While there have been significant efforts to address this problem, existing methods are still significantly limited in effectively detecting hate speech online. A major limi
Externí odkaz:
http://arxiv.org/abs/2401.03346
Autor:
Vishwamitra, Nishant, Guo, Keyan, Romit, Farhan Tajwar, Ondracek, Isabelle, Cheng, Long, Zhao, Ziming, Hu, Hongxin
Online hate is an escalating problem that negatively impacts the lives of Internet users, and is also subject to rapid changes due to evolving events, resulting in new waves of online hate that pose a critical threat. Detecting and mitigating these n
Externí odkaz:
http://arxiv.org/abs/2312.15099