1 code implementation • ICLR 2019 • Kaidi Xu, Sijia Liu, Pu Zhao, Pin-Yu Chen, huan zhang, Quanfu Fan, Deniz Erdogmus, Yanzhi Wang, Xue Lin
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example.
no code implementations • ICLR 2019 • Shaokai Ye, Tianyun Zhang, Kaiqi Zhang, Jiayu Li, Kaidi Xu, Yunfei Yang, Fuxun Yu, Jian Tang, Makan Fardad, Sijia Liu, Xiang Chen, Xue Lin, Yanzhi Wang
Motivated by dynamic programming, the proposed method reaches extremely high pruning rate by using partial prunings with moderate pruning rates.
2 code implementations • 23 Mar 2019 • Shaokai Ye, Xiaoyu Feng, Tianyun Zhang, Xiaolong Ma, Sheng Lin, Zhengang Li, Kaidi Xu, Wujie Wen, Sijia Liu, Jian Tang, Makan Fardad, Xue Lin, Yongpan Liu, Yanzhi Wang
A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results.
1 code implementation • 29 Mar 2019 • Shaokai Ye, Kaidi Xu, Sijia Liu, Jan-Henrik Lambrechts, huan zhang, Aojun Zhou, Kaisheng Ma, Yanzhi Wang, Xue Lin
Furthermore, this work studies two hypotheses about weight pruning in the conventional setting and finds that weight pruning is essential for reducing the network model size in the adversarial setting, training a small model from scratch even with inherited initialization from the large model cannot achieve both adversarial robustness and high standard accuracy.
no code implementations • 3 Apr 2019 • Kaidi Xu, Sijia Liu, Gaoyuan Zhang, Mengshu Sun, Pu Zhao, Quanfu Fan, Chuang Gan, Xue Lin
It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers.
no code implementations • 28 May 2019 • Shaokai Ye, Sia Huat Tan, Kaidi Xu, Yanzhi Wang, Chenglong Bao, Kaisheng Ma
On contrast, current state-of-the-art deep learning approaches heavily depend on the variety of training samples and the capacity of the network.
1 code implementation • 10 Jun 2019 • Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin
Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification.
1 code implementation • ICCV 2019 • Pu Zhao, Sijia Liu, Pin-Yu Chen, Nghia Hoang, Kaidi Xu, Bhavya Kailkhura, Xue Lin
Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse situations.
no code implementations • 29 Sep 2019 • Caiwen Ding, Shuo Wang, Ning Liu, Kaidi Xu, Yanzhi Wang, Yun Liang
To achieve real-time, highly-efficient implementations on FPGA, we present the detailed hardware implementation of block circulant matrices on CONV layers and develop an efficient processing element (PE) structure supporting the heterogeneous weight quantization, CONV dataflow and pipelining techniques, design optimization, and a template-based automatic synthesis framework to optimally exploit hardware resource.
1 code implementation • 30 Sep 2019 • Sijia Liu, Songtao Lu, Xiangyi Chen, Yao Feng, Kaidi Xu, Abdullah Al-Dujaili, Minyi Hong, Una-May O'Reilly
In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values.
1 code implementation • NeurIPS 2019 • Xiangyi Chen, Sijia Liu, Kaidi Xu, Xingguo Li, Xue Lin, Mingyi Hong, David Cox
In this paper, we propose a zeroth-order AdaMM (ZO-AdaMM) algorithm, that generalizes AdaMM to the gradient-free regime.
1 code implementation • ECCV 2020 • Kaidi Xu, Gaoyuan Zhang, Sijia Liu, Quanfu Fan, Mengshu Sun, Hongge Chen, Pin-Yu Chen, Yanzhi Wang, Xue Lin
To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to-rigid objects such as T-shirts.
1 code implementation • CVPR 2020 • Shaokai Ye, Kailu Wu, Mu Zhou, Yunfei Yang, Sia Huat Tan, Kaidi Xu, Jiebo Song, Chenglong Bao, Kaisheng Ma
Existing domain adaptation methods aim at learning features that can be generalized among domains.
Ranked #3 on Domain Adaptation on USPS-to-MNIST
no code implementations • 25 Feb 2020 • Kaidi Xu, Sijia Liu, Pin-Yu Chen, Mengshu Sun, Caiwen Ding, Bhavya Kailkhura, Xue Lin
To overcome these limitations, we propose a general framework which leverages the greedy search algorithms and zeroth-order methods to obtain robust GNNs in a generic and an efficient manner.
no code implementations • 26 Feb 2020 • Kaidi Xu, Sijia Liu, Pin-Yu Chen, Pu Zhao, Xue Lin
Although deep neural networks (DNNs) have achieved a great success in various computer vision tasks, it is recently found that they are vulnerable to adversarial attacks.
5 code implementations • NeurIPS 2020 • Kaidi Xu, Zhouxing Shi, huan zhang, Yihan Wang, Kai-Wei Chang, Minlie Huang, Bhavya Kailkhura, Xue Lin, Cho-Jui Hsieh
Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness verification and certified defense.
1 code implementation • 15 Jun 2020 • Qiyu Hu, Yunlong Cai, Qingjiang Shi, Kaidi Xu, Guanding Yu, Zhi Ding
Then, we implement the proposed deepunfolding framework to solve the sum-rate maximization problem for precoding design in MU-MIMO systems.
no code implementations • 23 Aug 2020 • Kaidi Xu, Ming-Min Zhao, Yunlong Cai, Lajos Hanzo
An unmanned aerial vehicle (UAV)-aided secure communication system is conceived and investigated, where the UAV transmits legitimate information to a ground user in the presence of an eavesdropper (Eve).
3 code implementations • ICLR 2021 • Kaidi Xu, huan zhang, Shiqi Wang, Yihan Wang, Suman Jana, Xue Lin, Cho-Jui Hsieh
Formal verification of neural networks (NNs) is a challenging and important problem.
no code implementations • 21 Dec 2020 • Pranay Sharma, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Xue Lin, Pramod K. Varshney
In this work, we focus on the study of stochastic zeroth-order (ZO) optimization which does not require first-order gradient information and uses only function evaluations.
1 code implementation • ICLR 2021 • Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Chuang Gan, Meng Wang
Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning.
4 code implementations • NeurIPS 2021 • Shiqi Wang, huan zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter
Compared to the typically tightest but very costly semidefinite programming (SDP) based incomplete verifiers, we obtain higher verified accuracy with three orders of magnitudes less verification time.
no code implementations • 21 Apr 2021 • Kaidi Xu, Chenan Wang, Hao Cheng, Bhavya Kailkhura, Xue Lin, Ryan Goldhahn
To tackle the susceptibility of deep neural networks to examples, the adversarial training has been proposed which provides a notion of robust through an inner maximization problem presenting the first-order embedded within the outer minimization of the training loss.
no code implementations • 15 Jun 2021 • Sheng Lin, Wei Jiang, Wei Wang, Kaidi Xu, Yanzhi Wang, Shan Liu, Songnan Li
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.
no code implementations • NeurIPS 2021 • Shiqi Wang, huan zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, J Zico Kolter
We develop $\beta$-CROWN, a new bound propagation based method that can fully encode neuron split constraints in branch-and-bound (BaB) based complete verification via optimizable parameters $\beta$.
no code implementations • 29 Sep 2021 • huan zhang, Shiqi Wang, Kaidi Xu, Yihan Wang, Suman Jana, Cho-Jui Hsieh, J Zico Kolter
In this work, we formulate an adversarial attack using a branch-and-bound (BaB) procedure on ReLU neural networks and search adversarial examples in the activation space corresponding to binary variables in a mixed integer programming (MIP) formulation.
no code implementations • 29 Sep 2021 • Quanfu Fan, Kaidi Xu, Chun-Fu Chen, Sijia Liu, Gaoyuan Zhang, David Daniel Cox, Xue Lin
Physical adversarial attacks apply carefully crafted adversarial perturbations onto real objects to maliciously alter the prediction of object classifiers or detectors.
no code implementations • NeurIPS 2021 • Husheng Han, Kaidi Xu, Xing Hu, Xiaobing Chen, Ling Liang, Zidong Du, Qi Guo, Yanzhi Wang, Yunji Chen
Our experimental results show that the certified accuracy is increased from 36. 3% (the state-of-the-art certified detection) to 60. 4% on the ImageNet dataset, largely pushing the certified defenses for practical use.
no code implementations • 12 Apr 2022 • Ling Liang, Kaidi Xu, Xing Hu, Lei Deng, Yuan Xie
To the best of our knowledge, this is the first analysis on robust training of SNNs.
2 code implementations • 11 Aug 2022 • huan zhang, Shiqi Wang, Kaidi Xu, Linyi Li, Bo Li, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter
Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods.
no code implementations • 19 Aug 2022 • Husheng Han, Xing Hu, Kaidi Xu, Pucheng Dang, Ying Wang, Yongwei Zhao, Zidong Du, Qi Guo, Yanzhi Yang, Tianshi Chen
This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection.
no code implementations • 20 Sep 2022 • Jiaqi Xue, Lei Xu, Lin Chen, Weidong Shi, Kaidi Xu, Qian Lou
(ii) How to design a robust PNet given the encrypted input without decryption?
1 code implementation • 15 Dec 2022 • Kaidi Xu, Nguyen Van Huynh, Geoffrey Ye Li
To overcome these limitations, we propose a multi-agent deep reinforcement learning (MADRL) based power control scheme for the HetNet, where each access point makes power control decisions independently based on local information.
1 code implementation • 2 Feb 2023 • Jinhao Duan, Fei Kong, Shiqi Wang, Xiaoshuang Shi, Kaidi Xu
In this paper, we investigate the vulnerability of diffusion models to Membership Inference Attacks (MIAs), a common privacy concern.
no code implementations • 28 Apr 2023 • Jinhao Duan, Quanfu Fan, Hao Cheng, Xiaoshuang Shi, Kaidi Xu
In this paper, we introduce Temporal Adversarial Augmentation (TA), a novel video augmentation technique that utilizes temporal attention.
1 code implementation • 26 May 2023 • Fei Kong, Jinhao Duan, RuiPeng Ma, HengTao Shen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu
Therefore, we also explore the robustness of diffusion models to MIA in the text-to-speech (TTS) task, which is an audio generation task.
no code implementations • 28 May 2023 • Jin Sun, Xiaoshuang Shi, Zhiyuan Wang, Kaidi Xu, Heng Tao Shen, Xiaofeng Zhu
Then, we build a pure-MLP architecture called Caterpillar by replacing the convolutional layer with the SPC module in a hybrid model of sMLPNet.
no code implementations • 2 Jun 2023 • Zhengyue Zhao, Jinhao Duan, Xing Hu, Kaidi Xu, Chenan Wang, Rui Zhang, Zidong Du, Qi Guo, Yunji Chen
This imperceptible protective noise makes the data almost unlearnable for diffusion models, i. e., diffusion models trained or fine-tuned on the protected data cannot generate high-quality and diverse images related to the protected training data.
1 code implementation • 3 Jun 2023 • Pucheng Dang, Xing Hu, Kaidi Xu, Jinhao Duan, Di Huang, Husheng Han, Rui Zhang, Zidong Du, Qi Guo, Yunji Chen
Unlearning techniques are proposed to prevent third parties from exploiting unauthorized data, which generate unlearnable samples by adding imperceptible perturbations to data for public publishing.
1 code implementation • 3 Jul 2023 • Jinhao Duan, Hao Cheng, Shiqi Wang, Alex Zavalny, Chenan Wang, Renjing Xu, Bhavya Kailkhura, Kaidi Xu
While Large Language Models (LLMs) have demonstrated remarkable potential in natural language generation and instruction following, a persistent challenge lies in their susceptibility to "hallucinations", which erodes trust in their outputs.
no code implementations • 12 Jul 2023 • RuiPeng Ma, Jinhao Duan, Fei Kong, Xiaoshuang Shi, Kaidi Xu
Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models.
no code implementations • ICCV 2023 • Ningfei Wang, Yunpeng Luo, Takami Sato, Kaidi Xu, Qi Alfred Chen
In this work, we conduct the first measurement study on whether and how effectively the existing designs can lead to system-level effects, especially for the STOP sign-evasion attacks due to their popularity and severity.
no code implementations • 31 Aug 2023 • Shenglong Zhou, Kaidi Xu, Geoffrey Ye Li
Compared to the centralized version, training a shared model among a large number of nodes in DFL is more challenging, as there is no central server to coordinate the training process.
1 code implementation • 14 Sep 2023 • Chenan Wang, Jinhao Duan, Chaowei Xiao, Edward Kim, Matthew Stamm, Kaidi Xu
Then there are two variants of this framework: 1) the Semantic Transformation (ST) approach fine-tunes the latent space of the generated image and/or the diffusion model itself; 2) the Latent Masking (LM) approach masks the latent space with another target image and local backpropagation-based interpretation methods.
no code implementations • 23 Sep 2023 • Hao Cheng, Jinhao Duan, Hui Li, Lyutianyang Zhang, Jiahang Cao, Ping Wang, Jize Zhang, Kaidi Xu, Renjing Xu
Recently, there has been a surge of interest and attention in Transformer-based structures, such as Vision Transformer (ViT) and Vision Multilayer Perceptron (VMLP).
no code implementations • 15 Oct 2023 • Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li
In this paper, we explore resource allocation in a V2X network under the framework of federated reinforcement learning (FRL).
no code implementations • 18 Nov 2023 • Hao Cheng, Jiahang Cao, Erjia Xiao, Mengshu Sun, Le Yang, Jize Zhang, Xue Lin, Bhavya Kailkhura, Kaidi Xu, Renjing Xu
It posits that within dense neural networks, there exist winning tickets or subnetworks that are sparser but do not compromise performance.
no code implementations • 21 Nov 2023 • Ren Wang, Ming Zhong, Kaidi Xu, Lola Giráldez Sánchez-Cortés, Ignacio de Cominges Guerra
This paper addresses the challenge of transient stability in power systems with missing parameters and uncertainty propagation in swing equations.
1 code implementation • 22 Nov 2023 • Yixin Liu, Kaidi Xu, Xun Chen, Lichao Sun
Observing that simply removing the adversarial noise on the training process of the defensive noise can improve the performance of robust unlearnable examples, we identify that solely the surrogate model's robustness contributes to the performance.
no code implementations • 23 Nov 2023 • Fei Kong, Jinhao Duan, Lichao Sun, Hao Cheng, Renjing Xu, HengTao Shen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu
Though diffusion models excel in image generation, their step-by-step denoising leads to slow generation speeds.
no code implementations • 30 Nov 2023 • Zhengyue Zhao, Jinhao Duan, Kaidi Xu, Chenan Wang, Rui Zhangp Zidong Dup Qi Guo, Xing Hu
Although these studies have demonstrated the ability to protect images, it is essential to consider that these methods may not be entirely applicable in real-world scenarios.
no code implementations • 4 Dec 2023 • Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, Yue Zhang
In the meantime, LLMs have also gained traction in the security community, revealing security vulnerabilities and showcasing their potential in security-related tasks.
no code implementations • 10 Dec 2023 • Amirhosein Chahe, Chenan Wang, Abhishek Jeyapratap, Kaidi Xu, Lifeng Zhou
Moreover, our method utilizes dynamic patches displayed on a screen, allowing for adaptive changes and movement, enhancing the flexibility and performance of the attack.
1 code implementation • 10 Jan 2024 • Lichao Sun, Yue Huang, Haoran Wang, Siyuan Wu, Qihui Zhang, Yuan Li, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, Zhengliang Liu, Yixin Liu, Yijue Wang, Zhikun Zhang, Bertie Vidgen, Bhavya Kailkhura, Caiming Xiong, Chaowei Xiao, Chunyuan Li, Eric Xing, Furong Huang, Hao liu, Heng Ji, Hongyi Wang, huan zhang, Huaxiu Yao, Manolis Kellis, Marinka Zitnik, Meng Jiang, Mohit Bansal, James Zou, Jian Pei, Jian Liu, Jianfeng Gao, Jiawei Han, Jieyu Zhao, Jiliang Tang, Jindong Wang, Joaquin Vanschoren, John Mitchell, Kai Shu, Kaidi Xu, Kai-Wei Chang, Lifang He, Lifu Huang, Michael Backes, Neil Zhenqiang Gong, Philip S. Yu, Pin-Yu Chen, Quanquan Gu, ran Xu, Rex Ying, Shuiwang Ji, Suman Jana, Tianlong Chen, Tianming Liu, Tianyi Zhou, William Wang, Xiang Li, Xiangliang Zhang, Xiao Wang, Xing Xie, Xun Chen, Xuyu Wang, Yan Liu, Yanfang Ye, Yinzhi Cao, Yong Chen, Yue Zhao
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
1 code implementation • 19 Feb 2024 • Jinhao Duan, Renming Zhang, James Diffenderfer, Bhavya Kailkhura, Lichao Sun, Elias Stengel-Eskin, Mohit Bansal, Tianlong Chen, Kaidi Xu
As Large Language Models (LLMs) are integrated into critical real-world applications, their strategic and logical reasoning abilities are increasingly crucial.
no code implementations • 22 Feb 2024 • Zhiyuan Wang, Jinhao Duan, Chenxi Yuan, Qingyu Chen, Tianlong Chen, Huaxiu Yao, Yue Zhang, Ren Wang, Kaidi Xu, Xiaoshuang Shi
Uncertainty estimation plays a pivotal role in ensuring the reliability of safety-critical human-AI interaction systems, particularly in the medical domain.
no code implementations • 29 Feb 2024 • Hao Cheng, Erjia Xiao, Jindong Gu, Le Yang, Jinhao Duan, Jize Zhang, Jiahang Cao, Kaidi Xu, Renjing Xu
Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language.
no code implementations • 15 Mar 2024 • Weixiang Sun, Yixin Liu, Zhiling Yan, Kaidi Xu, Lichao Sun
With the rapid growth of artificial intelligence (AI) in healthcare, there has been a significant increase in the generation and storage of sensitive medical data.
no code implementations • 18 Mar 2024 • Junyuan Hong, Jinhao Duan, Chenhui Zhang, Zhangheng Li, Chulin Xie, Kelsey Lieberman, James Diffenderfer, Brian Bartoldson, Ajay Jaiswal, Kaidi Xu, Bhavya Kailkhura, Dan Hendrycks, Dawn Song, Zhangyang Wang, Bo Li
While state-of-the-art (SoTA) compression methods boast impressive advancements in preserving benign task performance, the potential risks of compression in terms of safety and trustworthiness have been largely neglected.
1 code implementation • 12 Apr 2024 • Aref Azizpour, Tai D. Nguyen, Manil Shrestha, Kaidi Xu, Edward Kim, Matthew C. Stamm
To address these issues, we introduce the Ensemble of Expert Embedders (E3), a novel continual learning framework for updating synthetic image detectors.
no code implementations • ICML 2020 • Sijia Liu, Songtao Lu, Xiangyi Chen, Yao Feng, Kaidi Xu, Abdullah Al-Dujaili, Mingyi Hong, Una-May O'Reilly
In this paper, we study the problem of constrained min-max optimization in a black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values.