Zobrazeno 1 - 10
of 2 093
pro vyhledávání: '"Wang, Yichen"'
Autor:
Li, Chengzhengxu, Liu, Xiaoming, Zhang, Zhaohan, Wang, Yichen, Liu, Chen, Lan, Yu, Shen, Chao
Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts on domain generalization has been under-explored. To explore the natur
Externí odkaz:
http://arxiv.org/abs/2406.10584
Autor:
Deng, Chengyuan, Duan, Yiqun, Jin, Xin, Chang, Heng, Tian, Yijun, Liu, Han, Zou, Henry Peng, Jin, Yiqiao, Xiao, Yijia, Wang, Yichen, Wu, Shenghao, Xie, Zongxing, Gao, Kuofeng, He, Sihong, Zhuang, Jun, Cheng, Lu, Wang, Haohan
Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns, impacting the deployment of LLMs in everyday contexts. This paper pr
Externí odkaz:
http://arxiv.org/abs/2406.05392
Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context
Externí odkaz:
http://arxiv.org/abs/2405.03299
Autor:
Zhang, Hangtao, Hu, Shengshan, Wang, Yichen, Zhang, Leo Yu, Zhou, Ziqi, Wang, Xianlong, Zhang, Yanjun, Chen, Chao
Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adap
Externí odkaz:
http://arxiv.org/abs/2404.11357
Let $t,q$ and $n$ be positive integers. Write $[q] = \{1,2,\ldots,q\}$. The generalized Hamming graph $H(t,q,n)$ is the graph whose vertex set is the cartesian product of $n$ copies of $[q]$$(q\ge 2)$, where two vertices are adjacent if their Hamming
Externí odkaz:
http://arxiv.org/abs/2403.12549
Autor:
Wang, Yichen, Feng, Shangbin, Hou, Abe Bohan, Pu, Xiao, Shen, Chao, Liu, Xiaoming, Tsvetkov, Yulia, He, Tianxing
The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress test the detectors' robustness to malicious attacks under realistic scena
Externí odkaz:
http://arxiv.org/abs/2402.11638
Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection. While token-level watermarks are vulnerable to paraphrase attacks, SemStamp (Hou et al., 2023) applies watermark on the
Externí odkaz:
http://arxiv.org/abs/2402.11399
Autor:
Wang, Yichen, Lu, Mei
A star edge coloring of a graph $G$ is a proper edge coloring with no 2-colored path or cycle of length four. The star edge coloring problem is to find an edge coloring of a given graph $G$ with minimum number $k$ of colors such that $G$ admits a sta
Externí odkaz:
http://arxiv.org/abs/2402.04526
Autor:
Liu, Shengchao, Liu, Xiaoming, Wang, Yichen, Cheng, Zehua, Li, Chengzhengxu, Zhang, Zhaohan, Lan, Yu, Shen, Chao
The burgeoning generative capabilities of large language models (LLMs) have raised growing concerns about abuse, demanding automatic machine-generated text detectors. DetectGPT, a zero-shot metric-based detector, first introduces perturbation and sho
Externí odkaz:
http://arxiv.org/abs/2402.00263
Autor:
Wang, Yichen, Lv, Qin
Online user dynamics has been actively studied in recent years and bandwagon behavior is one of the most representative topics which can provide valuable insights for user identity change. Many previous studies have characterized bandwagon users and
Externí odkaz:
http://arxiv.org/abs/2401.11629