no code implementations • ICLR 2019 • Jinghui Chen, Quanquan Gu
Experiments on standard benchmarks show that Padam can maintain fast convergence rate as Adam/Amsgrad while generalizing as well as SGD in training deep neural networks.
no code implementations • 22 May 2024 • Tianrong Zhang, Bochuan Cao, Yuanpu Cao, Lu Lin, Prasenjit Mitra, Jinghui Chen
The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace.
no code implementations • 16 Feb 2024 • Ziyi Yin, Muchao Ye, Tianrong Zhang, Jiaqi Wang, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
Correspondingly, we propose a novel VQAttack model, which can iteratively generate both image and text perturbations with the designed modules: the large language model (LLM)-enhanced image attack and the cross-modal joint attack module.
no code implementations • 22 Dec 2023 • Tiejin Chen, Yuanpu Cao, Yujia Wang, Cho-Jui Hsieh, Jinghui Chen
Specifically, FedPTR allows local clients or the server to optimize an auxiliary (synthetic) dataset that mimics the learning dynamics of the recent model update and utilizes it to project the next-step model trajectory for local training regularization.
no code implementations • 14 Dec 2023 • Changjiang Li, Ren Pang, Bochuan Cao, Zhaohan Xi, Jinghui Chen, Shouling Ji, Ting Wang
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers.
no code implementations • 15 Nov 2023 • Yuanpu Cao, Bochuan Cao, Jinghui Chen
In this work, we show that it is possible to conduct stealthy and persistent unalignment on large language models via backdoor injections.
1 code implementation • NeurIPS 2023 • Bochuan Cao, Changjiang Li, Ting Wang, Jinyuan Jia, Bo Li, Jinghui Chen
IMPRESS is based on the key observation that imperceptible perturbations could lead to a perceptible inconsistency between the original image and the diffusion-reconstructed image, which can be used to devise a new optimization strategy for purifying the image, which may weaken the protection of the original image from unauthorized data usage (e. g., style mimicking, malicious editing).
1 code implementation • NeurIPS 2023 • Ziyi Yin, Muchao Ye, Tianrong Zhang, Tianyu Du, Jinguo Zhu, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks.
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?''.
1 code implementation • 18 Sep 2023 • Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen
In this work, we introduce a Robustly Aligned LLM (RA-LLM) to defend against potential alignment-breaking attacks.
1 code implementation • 19 Jan 2023 • Pei Fang, Jinghui Chen
Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data.
1 code implementation • 2 Oct 2022 • Lu Lin, Jinghui Chen, Hongning Wang
Graph contrastive learning (GCL), as an emerging self-supervised learning technique on graphs, aims to learn representations via instance discrimination.
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.
no code implementations • 10 Jul 2022 • Shuwen Chai, Jinghui Chen
Recent studies show that despite achieving high accuracy on a number of real-world applications, deep neural networks (DNNs) can be backdoored: by injecting triggered data samples into the training dataset, the adversary can mislead the trained model into classifying any test data to the target class as long as the trigger pattern is presented.
1 code implementation • 1 Jun 2022 • Hangzhi Guo, Feiran Jia, Jinghui Chen, Anna Squicciarini, Amulya Yadav
To address this problem, we propose RoCourseNet, a training framework that jointly optimizes predictions and recourses that are robust to future data shifts.
2 code implementations • 5 May 2022 • Yujia Wang, Lu Lin, Jinghui Chen
We show that in the nonconvex stochastic optimization setting, our proposed FedCAMS achieves the same convergence rate of $O(\frac{1}{\sqrt{TKm}})$ as its non-compressed counterparts.
1 code implementation • 15 Mar 2022 • Jooyoung Lee, Thai Le, Jinghui Chen, Dongwon Lee
Our results suggest that (1) three types of plagiarism widely exist in LMs beyond memorization, (2) both size and decoding methods of LMs are strongly associated with the degrees of plagiarism they exhibit, and (3) fine-tuned LMs' plagiarism patterns vary based on their corpus similarity and homogeneity.
no code implementations • ICLR 2022 • Weiqi Peng, Jinghui Chen
In particular, we propose adversarial invertible transformation, that can be viewed as a mapping from image to image, to slightly modify data samples so that they become "unlearnable" by machine learning models with negligible loss of visual features.
no code implementations • 31 Dec 2021 • Jinghui Chen, Yuan Cao, Quanquan Gu
Our result suggests that under moderate perturbations, adversarially trained linear classifiers can achieve the near-optimal standard and adversarial risks, despite overfitting the noisy training data.
no code implementations • 1 Nov 2021 • Yujia Wang, Lu Lin, Jinghui Chen
We prove that the proposed communication-efficient distributed adaptive gradient method converges to the first-order stationary point with the same iteration complexity as uncompressed vanilla AMSGrad in the stochastic nonconvex optimization setting.
1 code implementation • 3 Oct 2020 • Jinghui Chen, Yu Cheng, Zhe Gan, Quanquan Gu, Jingjing Liu
In this work, we develop a new understanding towards Fast Adversarial Training, by viewing random initialization as performing randomized smoothing for better optimization of the inner maximization problem.
1 code implementation • NeurIPS 2021 • Boxi Wu, Jinghui Chen, Deng Cai, Xiaofei He, Quanquan Gu
Previous empirical results suggest that adversarial training requires wider networks for better performances.
1 code implementation • 23 Jun 2020 • Jinghui Chen, Quanquan Gu
Deep neural networks are vulnerable to adversarial attacks.
Ranked #1 on Hard-label Attack on MNIST
1 code implementation • 1 Mar 2020 • Xiao Zhang, Jinghui Chen, Quanquan Gu, David Evans
Starting with Gilmer et al. (2018), several works have demonstrated the inevitability of adversarial examples based on different assumptions about the underlying input probability space.
no code implementations • 25 Sep 2019 • Jinghui Chen, Dongruo Zhou, Yiqi Tang, Ziyan Yang, Yuan Cao, Quanquan Gu
Experiments on standard benchmarks show that our proposed algorithm can maintain fast convergence rate as Adam/Amsgrad while generalizing as well as SGD in training deep neural networks.
2 code implementations • ICLR 2019 • Jinghui Chen, Dongruo Zhou, Jin-Feng Yi, Quanquan Gu
Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack.
no code implementations • 16 Aug 2018 • Dongruo Zhou, Jinghui Chen, Yuan Cao, Yiqi Tang, Ziyan Yang, Quanquan Gu
In this paper, we provide a fine-grained convergence analysis for a general class of adaptive gradient methods including AMSGrad, RMSProp and AdaGrad.
no code implementations • ICML 2018 • Jinghui Chen, Pan Xu, Lingxiao Wang, Jian Ma, Quanquan Gu
We propose a nonconvex estimator for the covariate adjusted precision matrix estimation problem in the high dimensional regime, under sparsity constraints.
2 code implementations • 18 Jun 2018 • Jinghui Chen, Dongruo Zhou, Yiqi Tang, Ziyan Yang, Yuan Cao, Quanquan Gu
Experiments on standard benchmarks show that our proposed algorithm can maintain a fast convergence rate as Adam/Amsgrad while generalizing as well as SGD in training deep neural networks.
no code implementations • NeurIPS 2018 • Pan Xu, Jinghui Chen, Difan Zou, Quanquan Gu
Furthermore, for the first time we prove the global convergence guarantee for variance reduced stochastic gradient Langevin dynamics (SVRG-LD) to the almost minimizer within $\tilde O\big(\sqrt{n}d^5/(\lambda^4\epsilon^{5/2})\big)$ stochastic gradient evaluations, which outperforms the gradient complexities of GLD and SGLD in a wide regime.
no code implementations • 20 Apr 2017 • Jinghui Chen, Lingxiao Wang, Xiao Zhang, Quanquan Gu
We consider the robust phase retrieval problem of recovering the unknown signal from the magnitude-only measurements, where the measurements can be contaminated by both sparse arbitrary corruption and bounded random noise.
no code implementations • 2 Jun 2016 • Jinghui Chen, Quanquan Gu
We propose a nonconvex estimator for joint multivariate regression and precision matrix estimation in the high dimensional regime, under sparsity constraints.