Search Results for author: Wenjie Ruan

Found 35 papers, 25 papers with code

Boosting Adversarial Training via Fisher-Rao Norm-based Regularization

no code implementations CVPR 2024 Xiangyu Yin, Wenjie Ruan

Then we generalize a complexity-related variable, which is sensitive to the changes in model width and the trade-off factors in adversarial training.

Adversarial Robustness

Towards Fairness-Aware Adversarial Learning

1 code implementation CVPR 2024 Yanghao Zhang, Tianle Zhang, Ronghui Mu, Xiaowei Huang, Wenjie Ruan

As a generalization of conventional AT, we re-define the problem of adversarial training as a min-max-max framework, to ensure both robustness and fairness of the trained model.


ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation

1 code implementation23 Feb 2024 Yi Zhang, Yun Tang, Wenjie Ruan, Xiaowei Huang, Siddartha Khastgir, Paul Jennings, Xingyu Zhao

Text-to-Image (T2I) Diffusion Models (DMs) have shown impressive abilities in generating high-quality images based on simple text descriptions.

Building Guardrails for Large Language Models

no code implementations2 Feb 2024 Yi Dong, Ronghui Mu, Gaojie Jin, Yi Qi, Jinwei Hu, Xingyu Zhao, Jie Meng, Wenjie Ruan, Xiaowei Huang

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies.

ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning

1 code implementation12 Dec 2023 Xiangyu Yin, Sihao Wu, Jiaxu Liu, Meng Fang, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan

Then, to mitigate the vulnerability of existing GCRL algorithms, we introduce Adversarial Representation Tactics, which combines Semi-Contrastive Adversarial Augmentation with Sensitivity-Aware Regularizer to improve the adversarial robustness of the underlying RL agent against various types of perturbations.

Adversarial Robustness reinforcement-learning

Reward Certification for Policy Smoothed Reinforcement Learning

no code implementations11 Dec 2023 Ronghui Mu, Leandro Soriano Marcolino, Tianle Zhang, Yanghao Zhang, Xiaowei Huang, Wenjie Ruan

Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks.

reinforcement-learning Reinforcement Learning (RL)

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation

no code implementations19 May 2023 Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, Andre Freitas, Mustafa A. Mustafa

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains.

Model-Agnostic Reachability Analysis on Deep Neural Networks

no code implementations3 Apr 2023 Chi Zhang, Wenjie Ruan, Fu Wang, Peipei Xu, Geyong Min, Xiaowei Huang

Verification plays an essential role in the formal analysis of safety-critical systems.

RePreM: Representation Pre-training with Masked Model for Reinforcement Learning

no code implementations3 Mar 2023 Yuanying Cai, Chuheng Zhang, Wei Shen, Xuyun Zhang, Wenjie Ruan, Longbo Huang

Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Representation Pre-training with Masked Model), which trains the encoder combined with transformer blocks to predict the masked states or actions in a trajectory.

Data Augmentation Language Modelling +3

Towards Verifying the Geometric Robustness of Large-scale Neural Networks

1 code implementation29 Jan 2023 Fu Wang, Peipei Xu, Wenjie Ruan, Xiaowei Huang

Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric transformation.

Reachability Analysis of Neural Network Control Systems

1 code implementation28 Jan 2023 Chi Zhang, Wenjie Ruan, Peipei Xu

We then reveal the working principles of applying Lipschitzian optimisation on NNCS verification and illustrate it by verifying an adaptive cruise control model.

Rolling Shutter Correction

Understanding Adversarial Robustness of Vision Transformers via Cauchy Problem

1 code implementation1 Aug 2022 Zheng Wang, Wenjie Ruan

Recent research on the robustness of deep learning has shown that Vision Transformers (ViTs) surpass the Convolutional Neural Networks (CNNs) under some perturbations, e. g., natural corruption, adversarial attacks, etc.

Adversarial Robustness

DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking

no code implementations17 Jul 2022 Xiangyu Yin, Wenjie Ruan, Jonathan Fieldsend

In this paper, we propose a novel adversarial attack method to generate noises for single object tracking under black-box settings, where perturbations are merely added on initial frames of tracking sequences, which is difficult to be noticed from the perspective of a whole video clip.

Adversarial Attack Miscellaneous +3

3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models

1 code implementation15 Jul 2022 Ronghui Mu, Wenjie Ruan, Leandro S. Marcolino, Qiang Ni

Thus, we propose an efficient verification framework, 3DVerifier, to tackle both challenges by adopting a linear relaxation function to bound the multiplication layer and combining forward and backward propagation to compute the certified bounds of the outputs of the point cloud models.

PRoA: A Probabilistic Robustness Assessment against Functional Perturbations

1 code implementation5 Jul 2022 Tianle Zhang, Wenjie Ruan, Jonathan E. Fieldsend

Our experiments demonstrate the effectiveness and flexibility of PRoA in terms of evaluating the probabilistic robustness against a broad range of functional perturbations, and PRoA can scale well to various large-scale deep neural networks compared to existing state-of-the-art baselines.

Sparse Adversarial Video Attacks with Spatial Transformations

1 code implementation10 Nov 2021 Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino, Qiang Ni

In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored.

Adversarial Attack Bayesian Optimisation +1

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications

no code implementations24 Aug 2021 Wenjie Ruan, Xinping Yi, Xiaowei Huang

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial examples.

Adversarial Robustness Learning Theory

Adversarial Driving: Attacking End-to-End Autonomous Driving

2 code implementations16 Mar 2021 Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom

As research in deep neural networks advances, deep convolutional networks become promising for autonomous driving tasks.

Autonomous Driving regression

Dynamic Efficient Adversarial Training Guided by Gradient Magnitude

1 code implementation4 Mar 2021 Fu Wang, Yanghao Zhang, Yanbin Zheng, Wenjie Ruan

Therefore, based on the magnitude of the gradient, we propose a general acceleration strategy, M+ acceleration, which enables an automatic and highly effective method of adjusting the training procedure.

Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks

1 code implementation4 Jan 2021 Yanghao Zhang, Fu Wang, Wenjie Ruan

Although there are a great number of adversarial attacks on deep learning based classifiers, how to attack object detection systems has been rarely studied.

Object object-detection +1

Generalizing Universal Adversarial Attacks Beyond Additive Perturbations

2 code implementations15 Oct 2020 Yanghao Zhang, Wenjie Ruan, Fu Wang, Xiaowei Huang

Extensive experiments are conducted on CIFAR-10 and ImageNet datasets with six deep neural network models including GoogleLeNet, VGG16/19, ResNet101/152, and DenseNet121.

Adversarial Attack

Towards the Quantification of Safety Risks in Deep Neural Networks

1 code implementation13 Sep 2020 Peipei Xu, Wenjie Ruan, Xiaowei Huang

In this paper, we define safety risks by requesting the alignment of the network's decision with human perception.

ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context

1 code implementation27 Nov 2019 Liantao Ma, Chaohe Zhang, Yasha Wang, Wenjie Ruan, Jiantao Wang, Wen Tang, Xinyu Ma, Xin Gao, Junyi Gao

Predicting the patient's clinical outcome from the historical electronic medical records (EMR) is a fundamental research problem in medical informatics.

AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration

1 code implementation27 Nov 2019 Liantao Ma, Junyi Gao, Yasha Wang, Chaohe Zhang, Jiangtao Wang, Wenjie Ruan, Wen Tang, Xin Gao, Xinyu Ma

It also models the correlation between clinical features to enhance the ones which strongly indicate the health status and thus can maintain a state-of-the-art performance in terms of prediction accuracy while providing qualitative interpretability.

Representation Learning

Coverage Guided Testing for Recurrent Neural Networks

1 code implementation5 Nov 2019 Wei Huang, Youcheng Sun, Xingyu Zhao, James Sharp, Wenjie Ruan, Jie Meng, Xiaowei Huang

The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks.

Defect Detection Drug Discovery +3

A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees

1 code implementation10 Jul 2018 Min Wu, Matthew Wicker, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska

In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the feature robustness problem, which aims to quantify the robustness of individual features to adversarial perturbations.

Adversarial Attack Adversarial Defense +2

Concolic Testing for Deep Neural Networks

2 code implementations30 Apr 2018 Youcheng Sun, Min Wu, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska, Daniel Kroening

Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program.

Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm

2 code implementations16 Apr 2018 Wenjie Ruan, Min Wu, Youcheng Sun, Xiaowei Huang, Daniel Kroening, Marta Kwiatkowska

In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples.

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