Zobrazeno 1 - 10
of 791
pro vyhledávání: '"Cheng Siyuan"'
Autor:
Yan, Lu, Cheng, Siyuan, Chen, Xuan, Zhang, Kaiyuan, Shen, Guangyu, Zhang, Zhuo, Zhang, Xiangyu
Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that systematically bypa
Externí odkaz:
http://arxiv.org/abs/2410.04009
Autor:
Feng, Shiwei, Chen, Xuan, Cheng, Zhiyuan, Xiong, Zikang, Gao, Yifei, Cheng, Siyuan, Kate, Sayali, Zhang, Xiangyu
Robot navigation is increasingly crucial across applications like delivery services and warehouse management. The integration of Reinforcement Learning (RL) with classical planning has given rise to meta-planners that combine the adaptability of RL w
Externí odkaz:
http://arxiv.org/abs/2409.10832
Autor:
Feng, Shiwei, Ye, Yapeng, Shi, Qingkai, Cheng, Zhiyuan, Xu, Xiangzhe, Cheng, Siyuan, Choi, Hongjun, Zhang, Xiangyu
As Autonomous driving systems (ADS) have transformed our daily life, safety of ADS is of growing significance. While various testing approaches have emerged to enhance the ADS reliability, a crucial gap remains in understanding the accidents causes.
Externí odkaz:
http://arxiv.org/abs/2409.07774
Autor:
Cheng, Siyuan, Shen, Guangyu, Zhang, Kaiyuan, Tao, Guanhong, An, Shengwei, Guo, Hanxi, Ma, Shiqing, Zhang, Xiangyu
Deep neural networks (DNNs) have demonstrated effectiveness in various fields. However, DNNs are vulnerable to backdoor attacks, which inject a unique pattern, called trigger, into the input to cause misclassification to an attack-chosen target label
Externí odkaz:
http://arxiv.org/abs/2407.11372
Autor:
Tian, Bozhong, Liang, Xiaozhuan, Cheng, Siyuan, Liu, Qingbin, Wang, Mengru, Sui, Dianbo, Chen, Xi, Chen, Huajun, Zhang, Ningyu
Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase specific k
Externí odkaz:
http://arxiv.org/abs/2407.01920
Autor:
Schaffner, Brennan, Bhagoji, Arjun Nitin, Cheng, Siyuan, Mei, Jacqueline, Shen, Jay L., Wang, Grace, Chetty, Marshini, Feamster, Nick, Lakier, Genevieve, Tan, Chenhao
Moderating user-generated content on online platforms is crucial for balancing user safety and freedom of speech. Particularly in the United States, platforms are not subject to legal constraints prescribing permissible content. Each platform has thu
Externí odkaz:
http://arxiv.org/abs/2405.05225
Autor:
Cheng, Siyuan, Tao, Guanhong, Liu, Yingqi, Shen, Guangyu, An, Shengwei, Feng, Shiwei, Xu, Xiangzhe, Zhang, Kaiyuan, Ma, Shiqing, Zhang, Xiangyu
Backdoor attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This susceptibility primarily stems from the fact that these attacks typically lev
Externí odkaz:
http://arxiv.org/abs/2403.17188
Autor:
Zhang, Ningyu, Tian, Bozhong, Cheng, Siyuan, Liang, Xiaozhuan, Hu, Yi, Xue, Kouying, Gou, Yanjie, Chen, Xi, Chen, Huajun
Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current approaches encounter issues with limited generalizability across tasks,
Externí odkaz:
http://arxiv.org/abs/2402.16123
Autor:
Li, Jiaqi, Du, Miaozeng, Zhang, Chuanyi, Chen, Yongrui, Hu, Nan, Qi, Guilin, Jiang, Haiyun, Cheng, Siyuan, Tian, Bozhong
Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs). Despite its potential, current benchmarks predominantly focus on coarse-grained knowledge, leaving the intricaci
Externí odkaz:
http://arxiv.org/abs/2402.14835
Autor:
Shen, Guangyu, Cheng, Siyuan, Zhang, Kaiyuan, Tao, Guanhong, An, Shengwei, Yan, Lu, Zhang, Zhuo, Ma, Shiqing, Zhang, Xiangyu
Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities. As they find increased use in sensitive tasks, safety concerns have gained widespread a
Externí odkaz:
http://arxiv.org/abs/2402.05467