Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Zhuang, Haomin"'
Autor:
Huang, Yue, Yuan, Zhengqing, Zhou, Yujun, Guo, Kehan, Wang, Xiangqi, Zhuang, Haomin, Sun, Weixiang, Sun, Lichao, Wang, Jindong, Ye, Yanfang, Zhang, Xiangliang
Large Language Models (LLMs) are increasingly employed for simulations, enabling applications in role-playing agents and Computational Social Science (CSS). However, the reliability of these simulations is under-explored, which raises concerns about
Externí odkaz:
http://arxiv.org/abs/2410.23426
Autor:
Zhou, Yujun, Han, Yufei, Zhuang, Haomin, Guo, Kehan, Liang, Zhenwen, Bao, Hongyan, Zhang, Xiangliang
Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications. However, concerns regarding their security, particularly the vulnerability to jailbreak attacks, persist. Drawing inspiration from adversarial training in d
Externí odkaz:
http://arxiv.org/abs/2402.13148
Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices. However, the decentralized learning paradigm and heterogeneity of FL further extend the attack surface for backdoor att
Externí odkaz:
http://arxiv.org/abs/2308.04466
The advancement of imaging devices and countless images generated everyday pose an increasingly high demand on image denoising, which still remains a challenging task in terms of both effectiveness and efficiency. To improve denoising quality, numero
Externí odkaz:
http://arxiv.org/abs/2304.08990
Despite the record-breaking performance in Text-to-Image (T2I) generation by Stable Diffusion, less research attention is paid to its adversarial robustness. In this work, we study the problem of adversarial attack generation for Stable Diffusion and
Externí odkaz:
http://arxiv.org/abs/2303.16378