Search Results for author: Haiqin Weng

Found 8 papers, 3 papers with code

RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainer

no code implementations3 Sep 2024 Jiangyi Deng, Xinfeng Li, Yanjiao Chen, Yijie Bai, Haiqin Weng, Yan Liu, Tao Wei, Wenyuan Xu

We have created a large-scale dataset for training and conducted extensive experiments to evaluate the capability of Raconteur in shell command explanation.

Course-Correction: Safety Alignment Using Synthetic Preferences

1 code implementation23 Jul 2024 Rongwu Xu, Yishuo Cai, Zhenhong Zhou, Renjie Gu, Haiqin Weng, Yan Liu, Tianwei Zhang, Wei Xu, Han Qiu

To improve, we propose fine-tuning LLMs with preference learning, emphasizing the preference for timely course-correction.

Safety Alignment

SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models

1 code implementation19 Apr 2024 Jiangyi Deng, Shengyuan Pang, Yanjiao Chen, Liangming Xia, Yijie Bai, Haiqin Weng, Wenyuan Xu

In addition, we carefully design the optimization process to entrap the pre-trained model within a hard-to-escape local optimum regarding restricted domains.

Meta-Learning

A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective

no code implementations6 Feb 2024 Lei Yu, Meng Han, Yiming Li, Changting Lin, Yao Zhang, Mingyang Zhang, Yan Liu, Haiqin Weng, Yuseok Jeon, Ka-Ho Chow, Stacy Patterson

Vertical Federated Learning (VFL) is a federated learning paradigm where multiple participants, who share the same set of samples but hold different features, jointly train machine learning models.

Survey Vertical Federated Learning

Exploring ChatGPT's Capabilities on Vulnerability Management

1 code implementation11 Nov 2023 Peiyu Liu, Junming Liu, Lirong Fu, Kangjie Lu, Yifan Xia, Xuhong Zhang, Wenzhi Chen, Haiqin Weng, Shouling Ji, Wenhai Wang

Prior works show that ChatGPT has the capabilities of processing foundational code analysis tasks, such as abstract syntax tree generation, which indicates the potential of using ChatGPT to comprehend code syntax and static behaviors.

Management

FDINet: Protecting against DNN Model Extraction via Feature Distortion Index

no code implementations20 Jun 2023 Hongwei Yao, Zheng Li, Haiqin Weng, Feng Xue, Zhan Qin, Kui Ren

FDINET exhibits the capability to identify colluding adversaries with an accuracy exceeding 91%.

Model extraction

Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks

no code implementations ICCV 2023 Xue Wang, Zhibo Wang, Haiqin Weng, Hengchang Guo, Zhifei Zhang, Lu Jin, Tao Wei, Kui Ren

Considering the insufficient study on such complex causal questions, we make the first attempt to explain different causal questions by contrastive explanations in a unified framework, ie., Counterfactual Contrastive Explanation (CCE), which visually and intuitively explains the aforementioned questions via a novel positive-negative saliency-based explanation scheme.

counterfactual

Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting

no code implementations3 Jun 2021 Ang Li, Qiuhong Ke, Xingjun Ma, Haiqin Weng, Zhiyuan Zong, Feng Xue, Rui Zhang

A promising countermeasure against such forgeries is deep inpainting detection, which aims to locate the inpainted regions in an image.

Image Inpainting

Cannot find the paper you are looking for? You can Submit a new open access paper.