Zobrazeno 1 - 10
of 1 476
pro vyhledávání: '"Hu, HaiBo"'
Autor:
Liang, Zi, Ye, Qingqing, Wang, Yanyun, Zhang, Sen, Xiao, Yaxin, Li, Ronghua, Xu, Jianliang, Hu, Haibo
Model extraction attacks (MEAs) on large language models (LLMs) have received increasing research attention lately. Existing attack methods on LLMs inherit the extraction strategies from those designed for deep neural networks (DNNs) yet neglect the
Externí odkaz:
http://arxiv.org/abs/2409.02718
The drastic increase of large language models' (LLMs) parameters has led to a new research direction of fine-tuning-free downstream customization by prompts, i.e., task descriptions. While these prompt-based services (e.g. OpenAI's GPTs) play an impo
Externí odkaz:
http://arxiv.org/abs/2408.02416
Answering range queries in the context of Local Differential Privacy (LDP) is a widely studied problem in Online Analytical Processing (OLAP). Existing LDP solutions all assume a uniform data distribution within each domain partition, which may not a
Externí odkaz:
http://arxiv.org/abs/2407.13532
Autor:
Li, Ziguang, Huang, Chao, Wang, Xuliang, Hu, Haibo, Wyeth, Cole, Bu, Dongbo, Yu, Quan, Gao, Wen, Liu, Xingwu, Li, Ming
Modern data compression methods are slowly reaching their limits after 80 years of research, millions of papers, and wide range of applications. Yet, the extravagant 6G communication speed requirement raises a major open question for revolutionary ne
Externí odkaz:
http://arxiv.org/abs/2407.07723
We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression. We demonstrate the equivalence of compression length under arithmetic coding w
Externí odkaz:
http://arxiv.org/abs/2406.14171
Autor:
Zhou, Zikang, Hu, Haibo, Chen, Xinhong, Wang, Jianping, Guan, Nan, Wu, Kui, Li, Yung-Hui, Huang, Yu-Kai, Xue, Chun Jason
Simulating realistic interactions among traffic agents is crucial for efficiently validating the safety of autonomous driving systems. Existing leading simulators primarily use an encoder-decoder structure to encode the historical trajectories for fu
Externí odkaz:
http://arxiv.org/abs/2405.17372
Time series have numerous applications in finance, healthcare, IoT, and smart city. In many of these applications, time series typically contain personal data, so privacy infringement may occur if they are released directly to the public. Recently, l
Externí odkaz:
http://arxiv.org/abs/2404.03873
Autor:
Deng, Ziheng, Chen, Hua, Zhou, Yongzheng, Hu, Haibo, Xu, Zhiyong, Sun, Jiayuan, Lyu, Tianling, Xi, Yan, Chen, Yang, Zhao, Jun
Four-dimensional cone-beam computed tomography (4D CBCT) provides respiration-resolved images and can be used for image-guided radiation therapy. However, the ability to reveal respiratory motion comes at the cost of image artifacts. As raw projectio
Externí odkaz:
http://arxiv.org/abs/2403.16361
With the exponential growth of data and its crucial impact on our lives and decision-making, the integrity of data has become a significant concern. Malicious data poisoning attacks, where false values are injected into the data, can disrupt machine
Externí odkaz:
http://arxiv.org/abs/2403.10313
Local differential privacy (LDP), which enables an untrusted server to collect aggregated statistics from distributed users while protecting the privacy of those users, has been widely deployed in practice. However, LDP protocols for frequency estima
Externí odkaz:
http://arxiv.org/abs/2403.09351