logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回
Z

Zhongliang Guo

University of St Andrews

7H指数
36论文数
137被引数
收录论文 11
发表时间
logo
Exploring backdoor attack and defense algorithms in LLMS: Enhancing in-context learning security探索LLMS中的后门攻击与防御算法：增强上下文学习安全性
errPattern Recognition
IF7.6
err2026-09-29
err0
PREAI
errShuai Zhao; Zhongliang Guo; Luwei Xiao; Cong-Duy Nguyen; Yanhao Jia; Xinyi Wu; Luu Anh Tuan
err分享
err收藏
Protecting Your Customized LLM Systems From Backdoored Instructions With Metacognitive Probing通过元认知探测保护您的定制化LLM系统免受后门指令的侵害
errIEEE Transactions on Information Forensics and Security
IF8
err2026-07-16
err0
PREAI
errShuai Zhao; Zhongliang Guo; Xinyi Wu; Xiaobao Wu; Yanhao Jia; Luwei Xiao; Anh Tuan Luu
err分享
err收藏
Rethinking 3D point cloud adversarial attacks from models' inherent focus从模型固有焦点重新审视三维点云对抗攻击
errExpert Systems with Applications
IF7.5
err2026-07-01
err0
PREAI
errYang, Li; Cai, Xiaowen; Chen, Shuqin; Dong, Junhao; Tang, Keke; Guo, Zhongliang; Liu, Daizong
err分享
err收藏
Attacking hard-label large vision-language models with model-sensitive adversarial patch designs攻击硬标签大型视觉语言模型的模型敏感对抗性贴片设计
errPattern Recognition
IF7.6
err2026-06-01
err0
PREAI
errAi, Nian; Chen, Guangke; Cai, Xiaowen; Guo, Zhongliang; Liu, Daizong; Zhou, Pan; Arandjelovic, Ognjen
err分享
err收藏
Backdoor defense for large language models with weak-to-strong knowledge distillation针对大型语言模型的防后门攻击方法：基于弱到强知识蒸馏
errPattern Recognition
IF7.6
err2026-01-02
err0
PREAI
errYuwen Li; Xinyi Wu; Zhongliang Guo; Luwei Xiao; Yanhao Jia; Shuai Zhao
err分享
err收藏
DiffProtect: Generative adversarial examples using diffusion models for facial privacy protectionDiffProtect: 基于扩散模型的生成对抗样本，用于面部隐私保护
errPattern Recognition
IF7.6
err2025-11-24
err0
errOAAI
errJiang Liu; Chun Pong Lau; Zhongliang Guo; Yuxiang Guo; Zhaoyang Wang; Rama Chellappa
err分享
err收藏
Artwork protection against unauthorized neural style transfer and aesthetic color distance metricartwork保护免受未经授权的神经风格迁移和美学颜色距离度量
errPattern Recognition
IF7.6
err2025-07-08
err0
PREAI
errZhongliang Guo; Yifei Qian; Shuai Zhao; Junhao Dong; Yanli Li; Ognjen Arandjelović; Lei Fang; Chun Pong Lau
err分享
err收藏
RVINN: a flexible modeling for inferring dynamic transcriptional and post-transcriptional regulation using physics-informed neural networksRVINN：一种基于物理信息神经网络的动态转录和转录后调控推断的灵活建模方法
errBIOINFORMATICS
IF5.4
err2025-07-01
err0
errOAAI
errMuto, Osamu; Guo, Zhongliang; Yamaguchi, Rui
err分享
err收藏
Syntactic paraphrase-based synthetic data generation for backdoor attacks against Chinese language models基于句法改写的中式语言模型后门攻击合成数据生成
errInformation Fusion
IF15.5
err2025-06-12
err0
PREAI
errMan Hu; Yatao Yang; Deng Pan; Zhongliang Guo; Luwei Xiao; Deyu Lin; Shuai Zhao
err分享
err收藏
Perspective-assisted prototype-based learning for semi-supervised crowd counting
errPATTERN RECOGNITION
IF7.6
err2025-02-01
err0
PREAI
errQian, Yifei; Zhang, Liangfei; Guo, Zhongliang; Hong, Xiaopeng; Arandjelovic, Ognjen; Donovan, Carl R.
err分享
err收藏
A Gray-Box Attack Against Latent Diffusion Model-Based Image Editing by Posterior Collapse一种基于后验塌陷的灰盒攻击方法，针对基于潜在扩散模型的图像编辑
errIEEE Transactions on Information Forensics and Security
IF8
err2025-01-01
err0
errOAAI
errZhongliang Guo; Chun Tong Lei; Lei Fang; Shuai Zhao; Yifei Qian; Jingyu Lin; Zeyu Wang; Cunjian Chen; Ognjen Arandjelović; Chun Pong Lau
err分享
err收藏

研究方向

暂时未获取到该数据
合作学者
合作期刊
R
Rama Chellappa
H 指数: 117 · 论文数: 1.3K
X
Xiaopeng Hong
H 指数: 45 · 论文数: 257
R
Rui Yamaguchi
H 指数: 43 · 论文数: 312
Z
Zhaoyang Wang
H 指数: 32 · 论文数: 135
O
Ognjen Arandjelović
H 指数: 32 · 论文数: 284
查看更多