Výsledky vyhledávání

Report

Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

Autor: Hu, Kai, Yu, Weichen, Yao, Tianjun, Li, Xiang, Liu, Wenhe, Yu, Lijun, Li, Yining, Chen, Kai, Shen, Zhiqiang, Fredrikson, Matt

Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained Optimization (ADC), w

Externí odkaz: http://arxiv.org/abs/2405.09113

Zobrazit plný text záznamu

Report

Debiasing Multimodal Large Language Models

Autor: Zhang, Yi-Fan, Yu, Weichen, Wen, Qingsong, Wang, Xue, Zhang, Zhang, Wang, Liang, Jin, Rong, Tan, Tieniu

In the realms of computer vision and natural language processing, Large Vision-Language Models (LVLMs) have become indispensable tools, proficient in generating textual descriptions based on visual inputs. Despite their advancements, our investigatio

Externí odkaz: http://arxiv.org/abs/2403.05262

Zobrazit plný text záznamu

Report

Bag of Tricks for Training Data Extraction from Language Models

Autor: Yu, Weichen, Pang, Tianyu, Liu, Qian, Du, Chao, Kang, Bingyi, Huang, Yan, Lin, Min, Yan, Shuicheng

With the advance of language models, privacy protection is receiving more attention. Training data extraction is therefore of great importance, as it can serve as a potential tool to assess privacy leakage. However, due to the difficulty of this task

Externí odkaz: http://arxiv.org/abs/2302.04460

Zobrazit plný text záznamu

Report

Generalized Inter-class Loss for Gait Recognition

Autor: Yu, Weichen, Yu, Hongyuan, Huang, Yan, Wang, Liang

Gait recognition is a unique biometric technique that can be performed at a long distance non-cooperatively and has broad applications in public safety and intelligent traffic systems. Previous gait works focus more on minimizing the intra-class vari

Externí odkaz: http://arxiv.org/abs/2210.06779

Zobrazit plný text záznamu

Report

CNTN: Cyclic Noise-tolerant Network for Gait Recognition

Autor: Yu, Weichen, Yu, Hongyuan, Huang, Yan, Cao, Chunshui, Wang, Liang

Gait recognition aims to identify individuals by recognizing their walking patterns. However, an observation is made that most of the previous gait recognition methods degenerate significantly due to two memorization effects, namely appearance memori

Externí odkaz: http://arxiv.org/abs/2210.06910

Zobrazit plný text záznamu

Report

Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting

Autor: Yu, Hongyuan, Li, Ting, Yu, Weichen, Li, Jianguo, Huang, Yan, Wang, Liang, Liu, Alex

Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal correlation simultaneously. However, most existing works focus more o

Externí odkaz: http://arxiv.org/abs/2210.06126

Zobrazit plný text záznamu