97 citations · 847 across the 68 of their papers we have counts for
71 papers
ToonTalker: Cross-Domain Face Reenactment
Yuan Gong, Yong Zhang, Xiaodong Cun +5
We target cross-domain face reenactment in this paper, i.e., driving a cartoon image with the video of a real person and vice versa. Recently, many works have focused on one-shot t…
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Shaokui Wei, Mingda Zhang, Hongyuan Zha +1
Backdoor attacks are serious security threats to machine learning models where an adversary can inject poisoned samples into the training set, causing a backdoored model which pred…
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Zihao Zhu, Mingda Zhang, Shaokui Wei +3
Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing at…
NOFA: NeRF-based One-shot Facial Avatar Reconstruction
Wangbo Yu, Yanbo Fan, Yong Zhang +8
3D facial avatar reconstruction has been a significant research topic in computer graphics and computer vision, where photo-realistic rendering and flexible controls over poses and…
DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
Zhiyuan Yan, Yong Zhang, Xinhang Yuan +2
A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. This issue leads to unfair perfor…
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
Mingli Zhu, Shaokui Wei, Hongyuan Zha +1
Recent studies have demonstrated the susceptibility of deep neural networks to backdoor attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be…
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
Ruotong Wang, Hongrui Chen, Zihao Zhu +2
Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on benign samples, dubbe…
Inter-frame Accelerate Attack against Video Interpolation Models
Junpei Liao, Zhikai Chen, Liang Yi +3
Deep learning based video frame interpolation (VIF) method, aiming to synthesis the intermediate frames to enhance video quality, have been highly developed in the past few years.…
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
Zixuan Hu, Li Shen, Zhenyi Wang +3
Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing…
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Mingli Zhu, Shaokui Wei, Li Shen +2
Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced by attackers, is becoming increasingly critical for machine learning security and int…
Improving Fast Adversarial Training with Prior-Guided Knowledge
Xiaojun Jia, Yong Zhang, Xingxing Wei +4
Fast adversarial training (FAT) is an efficient method to improve robustness. However, the original FAT suffers from catastrophic overfitting, which dramatically and suddenly reduc…
UCF: Uncovering Common Features for Generalizable Deepfake Detection
Zhiyuan Yan, Yong Zhang, Yanbo Fan +1
Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detecti…
DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks
Qiangqiang Wu, Tianyu Yang, Ziquan Liu +3
This paper studies masked autoencoder (MAE) video pre-training for various temporal matching-based downstream tasks, i.e., object-level tracking tasks including video object tracki…
Visual Prompt Based Personalized Federated Learning
Guanghao Li, Wansen Wu, Yan Sun +3
As a popular paradigm of distributed learning, personalized federated learning (PFL) allows personalized models to improve generalization ability and robustness by utilizing knowle…
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective
Baoyuan Wu, Zihao Zhu, Li Liu +3
Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans. Some paradigms have be…
Generalizable Black-Box Adversarial Attack with Meta Learning
Fei Yin, Yong Zhang, Baoyuan Wu +4
In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedb…
Visual Adversarial Attacks and Defenses in the Physical World: A Survey
Xingxing Wei, Bangzheng Pu, Shiji Zhao +2
Although Deep Neural Networks (DNNs) have been widely applied in various real-world scenarios, they remain vulnerable to adversarial examples. Adversarial attacks in computer visio…
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
Zeyu Qin, Yanbo Fan, Yi Liu +4
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work…
Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis
Jiancong Xiao, Zeyu Qin, Yanbo Fan +3
Adversarial Training (AT) has been demonstrated as one of the most effective methods against adversarial examples. While most existing works focus on AT with a single type of pertu…
Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning
Longkang Li, Siyuan Liang, Zihao Zhu +3
The permutation flow shop scheduling (PFSS), aiming at finding the optimal permutation of jobs, is widely used in manufacturing systems. When solving large-scale PFSS problems, tra…
A Large-scale Multiple-objective Method for Black-box Attack against Object Detection
Siyuan Liang, Longkang Li, Yanbo Fan +4
Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model info…
Imperceptible and Robust Backdoor Attack in 3D Point Cloud
Kuofeng Gao, Jiawang Bai, Baoyuan Wu +2
With the thriving of deep learning in processing point cloud data, recent works show that backdoor attacks pose a severe security threat to 3D vision applications. The attacker inj…
Versatile Weight Attack via Flipping Limited Bits
Jiawang Bai, Baoyuan Wu, Zhifeng Li +1
To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the…
Prior-Guided Adversarial Initialization for Fast Adversarial Training
Xiaojun Jia, Yong Zhang, Xingxing Wei +4
Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robus…