Zobrazeno 1 - 10
of 156
pro vyhledávání: '"Dong, Yinpeng"'
Autor:
Wei, Xingxing, Kang, Caixin, Dong, Yinpeng, Wang, Zhengyi, Ruan, Shouwei, Chen, Yubo, Su, Hang
Adversarial patches present significant challenges to the robustness of deep learning models, making the development of effective defenses become critical for real-world applications. This paper introduces DIFFender, a novel DIFfusion-based DeFender
Externí odkaz:
http://arxiv.org/abs/2409.09406
The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its security risks. The generated videos may contain illegal or unethical content, and there is a lack of comprehensiv
Externí odkaz:
http://arxiv.org/abs/2407.05965
Despite the great progress of 3D vision, data privacy and security issues in 3D deep learning are not explored systematically. In the domain of 2D images, many availability attacks have been proposed to prevent data from being illicitly learned by un
Externí odkaz:
http://arxiv.org/abs/2407.11011
Autor:
Zhang, Yichi, Huang, Yao, Sun, Yitong, Liu, Chang, Zhao, Zhe, Fang, Zhengwei, Wang, Yifan, Chen, Huanran, Yang, Xiao, Wei, Xingxing, Su, Hang, Dong, Yinpeng, Zhu, Jun
Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holi
Externí odkaz:
http://arxiv.org/abs/2406.07057
This paper studies the challenging black-box adversarial attack that aims to generate adversarial examples against a black-box model by only using output feedback of the model to input queries. Some previous methods improve the query efficiency by in
Externí odkaz:
http://arxiv.org/abs/2405.19098
Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render their defense mechanisms ineffective. However, previous jailbreak resear
Externí odkaz:
http://arxiv.org/abs/2405.19668
Autor:
Zhai, Shengfang, Chen, Huanran, Dong, Yinpeng, Li, Jiajun, Shen, Qingni, Gao, Yansong, Su, Hang, Liu, Yang
Text-to-image diffusion models have achieved tremendous success in the field of controllable image generation, while also coming along with issues of privacy leakage and data copyrights. Membership inference arises in these contexts as a potential au
Externí odkaz:
http://arxiv.org/abs/2405.14800
Autor:
Kong, Lingdong, Xie, Shaoyuan, Hu, Hanjiang, Niu, Yaru, Ooi, Wei Tsang, Cottereau, Benoit R., Ng, Lai Xing, Ma, Yuexin, Zhang, Wenwei, Pan, Liang, Chen, Kai, Liu, Ziwei, Qiu, Weichao, Zhang, Wei, Cao, Xu, Lu, Hao, Chen, Ying-Cong, Kang, Caixin, Zhou, Xinning, Ying, Chengyang, Shang, Wentao, Wei, Xingxing, Dong, Yinpeng, Yang, Bo, Jiang, Shengyin, Ma, Zeliang, Ji, Dengyi, Li, Haiwen, Huang, Xingliang, Tian, Yu, Kou, Genghua, Jia, Fan, Liu, Yingfei, Wang, Tiancai, Li, Ying, Hao, Xiaoshuai, Yang, Yifan, Zhang, Hui, Wei, Mengchuan, Zhou, Yi, Zhao, Haimei, Zhang, Jing, Li, Jinke, He, Xiao, Cheng, Xiaoqiang, Zhang, Bingyang, Zhao, Lirong, Ding, Dianlei, Liu, Fangsheng, Yan, Yixiang, Wang, Hongming, Ye, Nanfei, Luo, Lun, Tian, Yubo, Zuo, Yiwei, Cao, Zhe, Ren, Yi, Li, Yunfan, Liu, Wenjie, Wu, Xun, Mao, Yifan, Li, Ming, Liu, Jian, Liu, Jiayang, Qin, Zihan, Chu, Cunxi, Xu, Jialei, Zhao, Wenbo, Jiang, Junjun, Liu, Xianming, Wang, Ziyan, Li, Chiwei, Li, Shilong, Yuan, Chendong, Yang, Songyue, Liu, Wentao, Chen, Peng, Zhou, Bin, Wang, Yubo, Zhang, Chi, Sun, Jianhang, Chen, Hai, Yang, Xiao, Wang, Lizhong, Fu, Dongyi, Lin, Yongchun, Yang, Huitong, Li, Haoang, Luo, Yadan, Cheng, Xianjing, Xu, Yong
In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impa
Externí odkaz:
http://arxiv.org/abs/2405.08816
Vision-Language Pre-training (VLP) models like CLIP have achieved remarkable success in computer vision and particularly demonstrated superior robustness to distribution shifts of 2D images. However, their robustness under 3D viewpoint variations is
Externí odkaz:
http://arxiv.org/abs/2404.12139
Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility. However, f
Externí odkaz:
http://arxiv.org/abs/2404.11207