no code implementations • 28 Feb 2024 • Zhuoer Xu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang
Not only are these methods labor-intensive and require large budget costs, but the controllability of test prompt generation is lacking for the specific testing domain of LLM applications.
no code implementations • 15 Nov 2023 • Christian Mahoney, Peter Gronvall, Nathaniel Huber-Fliflet, Jianping Zhang
While interesting, manually annotating training text snippets is not generally practical during a legal document review.
2 code implementations • ICCV 2023 • Xiaosen Wang, Zeliang Zhang, Jianping Zhang
In this work, we find that the existing input transformation based attacks transform the input image globally, resulting in limited diversity of the transformed images.
no code implementations • 14 Sep 2023 • Yujie Feng, Yin Yang, Xiaohong Fan, Zhengpeng Zhang, Jianping Zhang
Furthermore, we propose a deep proximal mapping module in the image domain, which combines a generalized shrinkage threshold with a multi-scale prior feature extraction block.
1 code implementation • 8 Sep 2023 • Aoxu Liu, Xiaohong Fan, Yin Yang, Jianping Zhang
This network utilizes a learnable nonlinear transformation to address the proximal-point mapping sub-problem associated with the sparse priors, and an attention mechanism to focus on phase information containing image edges, textures, and structures.
no code implementations • 30 Aug 2023 • Zhuo-Xu Cui, Congcong Liu, Xiaohong Fan, Chentao Cao, Jing Cheng, Qingyong Zhu, Yuanyuan Liu, Sen Jia, Yihang Zhou, Haifeng Wang, Yanjie Zhu, Jianping Zhang, Qiegen Liu, Dong Liang
In order to enhance interpretability and overcome the acceleration limitations, this paper introduces an interpretable framework that unifies both $k$-space interpolation techniques and image-domain methods, grounded in the physical principles of heat diffusion equations.
no code implementations • ICCV 2023 • Zhuoer Xu, Zhangxuan Gu, Jianping Zhang, Shiwen Cui, Changhua Meng, Weiqiang Wang
Transfer-based attackers craft adversarial examples against surrogate models and transfer them to victim models deployed in the black-box situation.
1 code implementation • 6 Aug 2023 • Xiaohong Fan, Yin Yang, Ke Chen, Yujie Feng, Jianping Zhang
In the image restoration step, a cascade geometric incremental learning module is designed to compensate for missing texture information from different geometric spectral decomposition domains.
no code implementations • 4 Aug 2023 • Yanyan Li, Ke Chen, Chong Chen, Jianping Zhang
In this paper, we propose a new bi-variant diffeomorphic image registration model that introduces a soft constraint on the Jacobian equation $\det(\nabla\bm{\varphi}(\bm{x})) = f(\bm{x}) > 0$.
1 code implementation • 20 Jul 2023 • Wenwei Gu, Jinyang Liu, Zhuangbin Chen, Jianping Zhang, Yuxin Su, Jiazhen Gu, Cong Feng, Zengyin Yang, Michael Lyu
Performance issues permeate large-scale cloud service systems, which can lead to huge revenue losses.
1 code implementation • 14 Jun 2023 • Jianping Zhang, Zhuoer Xu, Shiwen Cui, Changhua Meng, Weibin Wu, Michael R. Lyu
Therefore, in this paper, we aim to analyze the robustness of latent diffusion models more thoroughly.
no code implementations • 2 Jun 2023 • Tiehua Zhang, Rui Xu, Jianping Zhang, Yuzhe Tian, Xin Chen, Xiaowei Huang, Jun Yin, Xi Zheng
Vulnerability detection is a critical problem in software security and attracts growing attention both from academia and industry.
no code implementations • 23 May 2023 • Wenxuan Wang, Jingyuan Huang, Chang Chen, Jiazhen Gu, Jianping Zhang, Weibin Wu, Pinjia He, Michael Lyu
To this end, content moderation software has been widely deployed on these platforms to detect and blocks toxic content.
2 code implementations • CVPR 2023 • Jianping Zhang, Yizhan Huang, Weibin Wu, Michael R. Lyu
However, the variance of the back-propagated gradients in intermediate blocks of ViTs may still be large, which may make the generated adversarial samples focus on some model-specific features and get stuck in poor local optima.
1 code implementation • CVPR 2023 • Jianping Zhang, Jen-tse Huang, Wenxuan Wang, Yichen Li, Weibin Wu, Xiaosen Wang, Yuxin Su, Michael R. Lyu
However, such methods selected the image augmentation path heuristically and may augment images that are semantics-inconsistent with the target images, which harms the transferability of the generated adversarial samples.
1 code implementation • 11 Feb 2023 • Wenxuan Wang, Jen-tse Huang, Weibin Wu, Jianping Zhang, Yizhan Huang, Shuqing Li, Pinjia He, Michael Lyu
In addition, we leverage the test cases generated by MTTM to retrain the model we explored, which largely improves model robustness (0% to 5. 9% EFR) while maintaining the accuracy on the original test set.
1 code implementation • 27 Oct 2022 • Hui Zhu, Shi Shu, Jianping Zhang
Based on the variational theory and FAS algorithm, we first design a feature extraction sub-network (FAS-Solution module) to solve the model-driven nonlinear systems, where a skip-connection is employed to fuse the multi-scale features.
1 code implementation • 14 May 2022 • Xiaohong Fan, Yin Yang, Ke Chen, Jianping Zhang, Ke Dong
Although existing deep learning compressed-sensing-based Magnetic Resonance Imaging (CS-MRI) methods have achieved considerably impressive performance, explainability and generalizability continue to be challenging for such methods since the transition from mathematical analysis to network design not always natural enough, often most of them are not flexible enough to handle multi-sampling-ratio reconstruction assignments.
1 code implementation • 13 May 2022 • Jen-tse Huang, Jianping Zhang, Wenxuan Wang, Pinjia He, Yuxin Su, Michael R. Lyu
However, in practice, many of the generated test cases fail to preserve similar semantic meaning and are unnatural (e. g., grammar errors), which leads to a high false alarm rate and unnatural test cases.
2 code implementations • CVPR 2022 • Jianping Zhang, Weibin Wu, Jen-tse Huang, Yizhan Huang, Wenxuan Wang, Yuxin Su, Michael R. Lyu
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples.
no code implementations • 20 Oct 2021 • Daoping Zhang, Gary P. T. Choi, Jianping Zhang, Lok Ming Lui
With the advancement of computer technology, there is a surge of interest in effective mapping methods for objects in higher-dimensional spaces.
1 code implementation • 11 Jul 2021 • Xiaohong Fan, Yin Yang, Jianping Zhang
Compressed sensing (CS) is an efficient method to reconstruct MR image from small sampled data in $k$-space and accelerate the acquisition of MRI.
no code implementations • 29 May 2021 • Srutarshi Banerjee, Henry H. Chopp, Jianping Zhang, Zihao W. Wang, Oliver Cossairt, Aggelos Katsaggelos
The detection and tracking of objects in the scene are done on the distorted data at the host.
no code implementations • 9 Feb 2021 • Rishi Chhatwal, Robert Keeling, Peter Gronvall, Nathaniel Huber-Fliflet, Jianping Zhang, Haozhen Zhao
As data volumes increase, legal counsel normally employs methods to reduce the number of documents requiring review while balancing the need to ensure the protection of privileged information.
no code implementations • 19 Dec 2019 • Robert Keeling, Rishi Chhatwal, Nathaniel Huber-Fliflet, Jianping Zhang, Fusheng Wei, Haozhen Zhao, Shi Ye, Han Qin
For each data set, classification models were trained with different training sample sizes using different learning algorithms.
no code implementations • 19 Dec 2019 • Christian J. Mahoney, Jianping Zhang, Nathaniel Huber-Fliflet, Peter Gronvall, Haozhen Zhao
This paper describes a framework for explainable text classification as a valuable tool in legal services: for enhancing the quality and efficiency of legal document review and for assisting in locating responsive snippets within responsive documents.
no code implementations • 11 Jun 2019 • Christian J. Mahoney, Nathaniel Huber-Fliflet, Haozhen Zhao, Jianping Zhang, Peter Gronvall, Shi Ye
In this study, we use extensive experimentation to examine the impact of popular seed set selection strategies in active learning, within a predictive coding exercise, and evaluate different active learning strategies against well-researched continuous active learning strategies for the purpose of determining efficient training methods for classifying large populations quickly and precisely.
no code implementations • 3 Apr 2019 • Peter Gronvall, Nathaniel Huber-Fliflet, Jianping Zhang, Robert Keeling, Robert Neary, Haozhen Zhao
Overly-inclusive keyword searching can also be problematic, because even while it drives up costs, it also can cast `too far of a net' and thus produce unreliable results. To overcome these weaknesses of keyword searching, legal teams are using a new method to target privileged information called predictive modeling.
no code implementations • 3 Apr 2019 • Rishi Chhatwal, Peter Gronvall, Nathaniel Huber-Fliflet, Robert Keeling, Jianping Zhang, Haozhen Zhao
In these scenarios, if predictive coding can be used to locate these responsive snippets, then attorneys could easily evaluate the model's document classification decision.
no code implementations • 3 Apr 2019 • Rishi Chhatwal, Nathaniel Huber-Fliflet, Robert Keeling, Jianping Zhang, Haozhen Zhao
One type of machine learning, text classification, is now regularly applied in the legal matters involving voluminous document populations because it can reduce the time and expense associated with the review of those documents.
no code implementations • 3 Apr 2019 • Rishi Chhatwal, Nathaniel Huber-Fliflet, Robert Keeling, Jianping Zhang, Haozhen Zhao
Predictive coding, once used in only a small fraction of legal and business matters, is now widely deployed to quickly cull through increasingly vast amounts of data and reduce the need for costly and inefficient human document review.
no code implementations • 6 Sep 2015 • Jianping Zhang, Ke Chen
In this paper we analyze and test a fractional-order derivative based total $\alpha$-order variation model, which can outperform the currently popular high order regularization models.