no code implementations • 12 Feb 2025 • Hangfan Zhang, Zhiyao Cui, Xinrun Wang, Qiaosheng Zhang, Zhen Wang, Dinghao Wu, Shuyue Hu
Multi-agent debate (MAD) has emerged as a promising approach to enhance the factual accuracy and reasoning quality of large language models (LLMs) by engaging multiple agents in iterative discussions during inference.
1 code implementation • 4 Jun 2024 • Songtao Liu, Jinghui Chen, Tianfan Fu, Lu Lin, Marinka Zitnik, Dinghao Wu
This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem.
no code implementations • 2 Oct 2023 • Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu, Bochuan Cao, Lu Lin, Jinyuan Jia, Jinghui Chen, Dinghao Wu
A natural question is "could alignment really prevent those open-sourced large language models from being misused to generate undesired content?''.
no code implementations • 4 Jun 2023 • Xiaoting Li, Lingwei Chen, Dinghao Wu
To address this challenge, in this paper, we leverage the inherent vulnerability of machine learning to adversarial attacks, and design a novel text-space Adversarial attack for Social Good, called Adv4SG.
1 code implementation • 30 Sep 2022 • Songtao Liu, Zhengkai Tu, Minkai Xu, Zuobai Zhang, Lu Lin, Rex Ying, Jian Tang, Peilin Zhao, Dinghao Wu
Current strategies use a decoupled approach of single-step retrosynthesis models and search algorithms, taking only the product as the input to predict the reactants for each planning step and ignoring valuable context information along the synthetic route.
no code implementations • 29 Sep 2022 • Songtao Liu, Rex Ying, Hanze Dong, Lu Lin, Jinghui Chen, Dinghao Wu
However, the analysis of implicit denoising effect in graph neural networks remains open.
1 code implementation • 8 Sep 2021 • Songtao Liu, Rex Ying, Hanze Dong, Lanqing Li, Tingyang Xu, Yu Rong, Peilin Zhao, Junzhou Huang, Dinghao Wu
To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node features of the neighbors conditioned on the central node's feature and enhance GNN's expressive power with generated features.
no code implementations • 29 Jul 2021 • Michalis Kallitsis, Vasant Honavar, Rupesh Prajapati, Dinghao Wu, John Yen
Network telescopes or "Darknets" provide a unique window into Internet-wide malicious activities associated with malware propagation, denial of service attacks, scanning performed for network reconnaissance, and others.
no code implementations • 11 Nov 2019 • Songtao Liu, Lingwei Chen, Hanze Dong, ZiHao Wang, Dinghao Wu, Zengfeng Huang
Graph Convolution Network (GCN) has been recognized as one of the most effective graph models for semi-supervised learning, but it extracts merely the first-order or few-order neighborhood information through information propagation, which suffers performance drop-off for deeper structure.
no code implementations • 5 Jan 2016 • Pei Wang, Shuai Wang, Jiang Ming, Yufei Jiang, Dinghao Wu
We introduce translingual obfuscation, a new software obfuscation scheme which makes programs obscure by "misusing" the unique features of certain programming languages.
Cryptography and Security Software Engineering