1 code implementation • 28 Apr 2024 • Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu
Large Language Models (LLMs) have highlighted the necessity of effective unlearning mechanisms to comply with data regulations and ethical AI practices.
1 code implementation • 19 Feb 2024 • Yihua Zhang, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Xiaoming Liu, Sijia Liu
The rapid advancement of diffusion models (DMs) has not only transformed various real-world industries but has also introduced negative societal concerns, including the generation of harmful content, copyright disputes, and the rise of stereotypes and biases.
no code implementations • 13 Feb 2024 • Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Xiaojun Xu, Yuguang Yao, Hang Li, Kush R. Varshney, Mohit Bansal, Sanmi Koyejo, Yang Liu
We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning.
1 code implementation • 12 Dec 2023 • Shijun Liang, Van Hoang Minh Nguyen, Jinghan Jia, Ismail Alkhouri, Sijia Liu, Saiprasad Ravishankar
To address this problem, we propose a novel image reconstruction framework, termed Smoothed Unrolling (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust learning approach.
1 code implementation • 18 Oct 2023 • Yimeng Zhang, Jinghan Jia, Xin Chen, Aochuan Chen, Yihua Zhang, Jiancheng Liu, Ke Ding, Sijia Liu
Our results demonstrate the effectiveness and efficiency merits of UnlearnDiffAtk over the state-of-the-art adversarial prompt generation method and reveal the lack of robustness of current safety-driven unlearning techniques when applied to DMs.
1 code implementation • 3 Oct 2023 • Aochuan Chen, Yimeng Zhang, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu
Our extensive experiments show that DeepZero achieves state-of-the-art (SOTA) accuracy on ResNet-20 trained on CIFAR-10, approaching FO training performance for the first time.
1 code implementation • NeurIPS 2023 • Jinghan Jia, Jiancheng Liu, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
We show in both theory and practice that model sparsity can boost the multi-criteria unlearning performance of an approximate unlearner, closing the approximation gap, while continuing to be efficient.
2 code implementations • 14 Mar 2023 • Hui Li, Jinghan Jia, Shijun Liang, Yuguang Yao, Saiprasad Ravishankar, Sijia Liu
To address this problem, we propose a novel image reconstruction framework, termed SMOOTHED UNROLLING (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust learning operation.
1 code implementation • CVPR 2023 • Yimeng Zhang, Xin Chen, Jinghan Jia, Sijia Liu, Ke Ding
In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video.
no code implementations • 7 Mar 2023 • Jinghan Jia, Yihua Zhang, Dogyoon Song, Sijia Liu, Alfred Hero
Most work in this learning paradigm has focused on resolving the problem of 'catastrophic forgetting,' which refers to a notorious dilemma between improving model accuracy over new data and retaining accuracy over previous data.
1 code implementation • 19 Dec 2022 • Bairu Hou, Jinghan Jia, Yihua Zhang, Guanhua Zhang, Yang Zhang, Sijia Liu, Shiyu Chang
Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP).
1 code implementation • 21 Nov 2022 • Jinghan Jia, Shashank Srikant, Tamara Mitrovska, Chuang Gan, Shiyu Chang, Sijia Liu, Una-May O'Reilly
We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models.
no code implementations • 9 Nov 2022 • Jinghan Jia, Mingyi Hong, Yimeng Zhang, Mehmet Akçakaya, Sijia Liu
We find a new instability source of MRI image reconstruction, i. e., the lack of reconstruction robustness against spatial transformations of an input, e. g., rotation and cutout.
1 code implementation • ICLR 2022 • Yimeng Zhang, Yuguang Yao, Jinghan Jia, JinFeng Yi, Mingyi Hong, Shiyu Chang, Sijia Liu
To tackle this problem, we next propose to prepend an autoencoder (AE) to a given (black-box) model so that DS can be trained using variance-reduced ZO optimization.
no code implementations • 25 Feb 2021 • Chi Zhang, Jinghan Jia, Burhaneddin Yaman, Steen Moeller, Sijia Liu, Mingyi Hong, Mehmet Akçakaya
Although deep learning (DL) has received much attention in accelerated MRI, recent studies suggest small perturbations may lead to instabilities in DL-based reconstructions, leading to concern for their clinical application.