Zobrazeno 1 - 10
of 8 625
pro vyhledávání: '"chaowei an"'
Using multiple sensors to update the status process of interest is promising in improving the information freshness. The unordered arrival of status updates at the monitor end poses a significant challenge in analyzing the timeliness performance of p
Externí odkaz:
http://arxiv.org/abs/2412.08277
Autor:
Sun, Ruoxi, Chang, Jiamin, Pearce, Hammond, Xiao, Chaowei, Li, Bo, Wu, Qi, Nepal, Surya, Xue, Minhui
Multimodal foundation models (MFMs) represent a significant advancement in artificial intelligence, combining diverse data modalities to enhance learning and understanding across a wide range of applications. However, this integration also brings uni
Externí odkaz:
http://arxiv.org/abs/2411.11195
Autor:
Yang, Ying, Cheng, De, Fang, Chaowei, Wang, Yubiao, Jiao, Changzhe, Cheng, Lechao, Wang, Nannan
Publikováno v:
Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)
Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is crucial for developing a safe real-world machine learning system. Current reconstruct
Externí odkaz:
http://arxiv.org/abs/2411.10701
Autor:
Ma, Yingzi, Wang, Jiongxiao, Wang, Fei, Ma, Siyuan, Li, Jiazhao, Li, Xiujun, Huang, Furong, Sun, Lichao, Li, Bo, Choi, Yejin, Chen, Muhao, Xiao, Chaowei
Machine unlearning has emerged as an effective strategy for forgetting specific information in the training data. However, with the increasing integration of visual data, privacy concerns in Vision Language Models (VLMs) remain underexplored. To addr
Externí odkaz:
http://arxiv.org/abs/2411.03554
Autor:
Wang, Jiongxiao, Wu, Fangzhou, Li, Wendi, Pan, Jinsheng, Suh, Edward, Mao, Z. Morley, Chen, Muhao, Xiao, Chaowei
Large language models (LLMs) have been widely deployed as the backbone with additional tools and text information for real-world applications. However, integrating external information into LLM-integrated applications raises significant security conc
Externí odkaz:
http://arxiv.org/abs/2410.21492
Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is uniformly blocked to all the users. However, this part of knowledge can be
Externí odkaz:
http://arxiv.org/abs/2410.14676
In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (LLMs). Despite rigorous pretraining and finetuning focused on ethical a
Externí odkaz:
http://arxiv.org/abs/2410.08660
Autor:
He, Xiaoxiao, Han, Ligong, Dao, Quan, Wen, Song, Bai, Minhao, Liu, Di, Zhang, Han, Min, Martin Renqiang, Juefei-Xu, Felix, Tan, Chaowei, Liu, Bo, Li, Kang, Li, Hongdong, Huang, Junzhou, Ahmed, Faez, Srivastava, Akash, Metaxas, Dimitris
Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (Discrete Inversion for Controllable Editing), the first approach to ena
Externí odkaz:
http://arxiv.org/abs/2410.08207
Autor:
Kumarappan, Adarsh, Tiwari, Mo, Song, Peiyang, George, Robert Joseph, Xiao, Chaowei, Anandkumar, Anima
Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existing approaches involve training or fine-tuning an LLM on a specific dat
Externí odkaz:
http://arxiv.org/abs/2410.06209
Autor:
Liu, Xiaogeng, Li, Peiran, Suh, Edward, Vorobeychik, Yevgeniy, Mao, Zhuoqing, Jha, Somesh, McDaniel, Patrick, Sun, Huan, Li, Bo, Xiao, Chaowei
In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human intervention or predefined scopes (e.g., specified candidate strategies), a
Externí odkaz:
http://arxiv.org/abs/2410.05295