17 citations · 69 across the 17 of their papers we have counts for
18 papers
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
Zhenxing Niu, Yuyao Sun, Qiguang Miao +2
Deep Neural Networks (DNNs) are known to be vulnerable to both backdoor and adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct robu…
Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
Haoxuan Ji, Zheng Lin, Zhenxing Niu +2
This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previo…
Jailbreaking Attack against Multimodal Large Language Model
Zhenxing Niu, Haodong Ren, Xinbo Gao +2
This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries. A…
Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Ones
Junyi Li, Xiaohe Wu, Zhenxing Niu +1
While significant progress has been made in deep video denoising, it remains very challenging for exploiting historical and future frames. Bidirectional recurrent networks (BiRNN)…
Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis
Zhengyao Lv, Xiaoming Li, Zhenxing Niu +2
Recent years have witnessed substantial progress in semantic image synthesis, it is still challenging in synthesizing photo-realistic images with rich details. Most previous method…
Towards Simple and Accurate Human Pose Estimation with Stair Network
Chenru Jiang, Kaizhu Huang, Shufei Zhang +3
In this paper, we focus on tackling the precise keypoint coordinates regression task. Most existing approaches adopt complicated networks with a large number of parameters, leading…
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Bingxu Mu, Zhenxing Niu, Le Wang +3
Deep neural networks (DNNs) are known to be vulnerable to both backdoor attacks as well as adversarial attacks. In the literature, these two types of attacks are commonly treated a…
Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters
Bowen Dong, Zitong Huang, Yuelin Guo +3
Weakly-supervised object detection (WSOD) has emerged as an inspiring recent topic to avoid expensive instance-level object annotations. However, the bounding boxes of most existin…
Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction
Fang Zheng, Le Wang, Sanping Zhou +4
Understanding complex social interactions among agents is a key challenge for trajectory prediction. Most existing methods consider the interactions between pairwise traffic agents…
Adversarial Attack and Defense in Deep Ranking
Mo Zhou, Le Wang, Zhenxing Niu +3
Deep Neural Network classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based…
Video Imprint
Zhanning Gao, Le Wang, Nebojsa Jojic +3
A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploit…
Structure First Detail Next: Image Inpainting with Pyramid Generator
Shuyi Qu, Zhenxing Niu, Kaizhu Huang +4
Recent deep generative models have achieved promising performance in image inpainting. However, it is still very challenging for a neural network to generate realistic image detail…
Image Inpainting with Edge-guided Learnable Bidirectional Attention Maps
Dongsheng Wang, Chaohao Xie, Shaohui Liu +2
For image inpainting, the convolutional neural networks (CNN) in previous methods often adopt standard convolutional operator, which treats valid pixels and holes indistinguishably…
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Liushuai Shi, Le Wang, Chengjiang Long +4
Pedestrian trajectory prediction is a key technology in autopilot, which remains to be very challenging due to complex interactions between pedestrians. However, previous works bas…
Practical Relative Order Attack in Deep Ranking
Mo Zhou, Le Wang, Zhenxing Niu +4
Recent studies unveil the vulnerabilities of deep ranking models, where an imperceptible perturbation can trigger dramatic changes in the ranking result. While previous attempts fo…
Adversarial Ranking Attack and Defense
Mo Zhou, Zhenxing Niu, Le Wang +2
Deep Neural Network (DNN) classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN…
Ladder Loss for Coherent Visual-Semantic Embedding
Mo Zhou, Zhenxing Niu, Le Wang +3
For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way -- relevant or irrelevant, and all "irrelevant" can…
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
Jinliang Zang, Le Wang, Ziyi Liu +4
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However,…