Search Results for author: Ming Ma

Found 9 papers, 1 papers with code

Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

no code implementations7 Dec 2023 Yanrui Du, Sendong Zhao, Ming Ma, Yuhan Chen, Bing Qin

The jailbreak idea of our method is "Inherent Response Tendency Analysis" which identifies real-world instructions that can inherently induce LLMs to generate affirmation responses and the corresponding jailbreak strategy is "Real-World Instructions-Driven Jailbreak" which involves strategically splicing real-world instructions identified through the above analysis around the malicious instruction.

Robustness-enhanced Uplift Modeling with Adversarial Feature Desensitization

no code implementations7 Oct 2023 Zexu Sun, Bowei He, Ming Ma, Jiakai Tang, Yuchen Wang, Chen Ma, Dugang Liu

Specifically, our RUAD can more effectively alleviate the feature sensitivity of the uplift model through two customized modules, including a feature selection module with joint multi-label modeling to identify a key subset from the input features and an adversarial feature desensitization module using adversarial training and soft interpolation operations to enhance the robustness of the model against this selected subset of features.

feature selection Marketing

Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain

1 code implementation8 Sep 2023 Yanrui Du, Sendong Zhao, MuZhen Cai, Ming Ma, Danyang Zhao, Jiawei Cao, Bing Qin

We conduct several experiments to analyze the dual logic ability of LLMs by examining the consistency of the stance in responses to paired questions about the same fact.

Fact Checking Knowledge Graphs

CWP: Instance complexity weighted channel-wise soft masks for network pruning

no code implementations8 Sep 2022 Jiapeng Wang, Ming Ma, Zhenhua Yu

In this paper, we propose a simple yet effective differentiable network pruning method CWP based on instance complexity weighted filter importance scores.

Network Pruning

a novel attention-based network for fast salient object detection

no code implementations20 Dec 2021 Bin Zhang, Yang Wu, Xiaojing Zhang, Ming Ma

In the current salient object detection network, the most popular method is using U-shape structure.

Object object-detection +2

Atlas Based Segmentations via Semi-Supervised Diffeomorphic Registrations

no code implementations23 Nov 2019 Charles Huang, Masoud Badiei, Hyunseok Seo, Ming Ma, Xiaokun Liang, Dante Capaldi, Michael Gensheimer, Lei Xing

Whereas supervised segmentation methods only automate the segmentation process for a select few number of OARs, we demonstrate that our methods can achieve similar performance for OARs of interest, while also providing segmentations for every other OAR on the provided atlas.

Segmentation

Count-guided Weakly Supervised Localization Based on Density Map

no code implementations25 Sep 2019 Ming Ma, Stephan Chalup, Fayeem Aziz, Yang Liu, Defu Cheng, Zhijian Zhou

In this paper, we generalize WSL to counting machines that apply convolutional neural networks (CNN) and density maps for counting.

Crowd Counting

Surface Registration via Foliation

no code implementations ICCV 2017 Xiaopeng Zheng, Chengfeng Wen, Na lei, Ming Ma, Xianfeng GU

This work introduces a novel surface registration method based on foliation.

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