|
对抗攻防学习
深度神经网络目前已经获得了突破式发展,并且在多个领域得到了广泛应用。
然而,深度神经网络同样面临着被攻击的威胁,也就是“对抗样本”:
攻击者通过在源数据上增加难以通过感官辨识到的细微改变,让神经网络模型做出错误的分类决定。
本团队通过研究对抗样本的生成原理和算法实现,有助于分析基于深度学习的系统存在的安全漏洞,
并针对此类攻击建立更好的防范机制,加速机器学习领域的进步。
相关链接:
1. FaceBook AI:对抗攻防学习研究、
鲁棒性分析
2. 对抗攻防学习综艺节目:《燃烧吧!天才程序员》
LAFED: Towards Robust Ensemble Models Via Latent Feature Diversification
Wenzi Zhuang, Lifeng Huang, Chengying Gao, Ning Liu*
|
|
FASTEN: Fast Ensemble Learning For Improved Adversarial Robustness
Lifeng Huang, Qiong Huang, Peichao Qiu, Shuxin Wei, Chengying Gao*
|
|
Erosion Attack: Harnessing Corruption To Improve Adversarial Examples
Lifeng Huang, Chengying Gao*, Ning Liu
|
|
DEFEAT: Decoupled Feature Attack Across Deep Neural Networks
Lifeng Huang, Chengying Gao, Ning Liu
|
|
Cyclical Adversarial Attack Pierces Black-box Deep Neural Networks
Lifeng Huang, Shuxin Wei, Chengying Gao, Ning Liu
|
|
Enhancing Adversarial Examples Via Self-Augmentation
Lifeng Huang, Wenzi Zhuang, Chengying Gao, Ning Liu
|
|
一种基于进化策略和注意力机制的黑盒对抗攻击算法
黄立峰,庄文梓,廖泳贤,刘宁
|
|
Universal Physical Camouflage Attacks on Object Detectors
Lifeng Huang, Chengying Gao, Yuyin Zhou, Changqing Zou, Cihang Xie, Alan Yuille, Ning Liu
|
|
G-UAP: Generic Universal Adversarial Perturbation that Fools RPN-based Detectors
Xing wu, Lifeng Huang, Chengying Gao*
|
人群计数
行人检测与属性分析通过视频分析,实现对监控区域中的人群人数分布、人群外观属性、行人运动轨迹进行精确分析,
该研究在安防监控、自动驾驶及线下商业领域具有重要的意义。
相关链接:
1. 香港城市大学 人群计数研究:资料1、
资料2
Scale-aware Progressive Optimization Network
Ying Chen, Lifeng Huang, Chengying Gao, Ning Liu
|
|
Self-Bootstrapping Pedestrian Detection in Downward-Viewing Fisheye Cameras Using Pseudo-Labeling
Kaishi Gao, Qun Niu, Haoquan You, Chengying Gao
|
|
Scale-Aware Rolling Fusion Network for Crowd Counting
Ying Chen, Chengying Gao, Zhuo Su, Xiangjian He, Ning Liu
|
|
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding
Ning Liu, Yongchao Long, Changqing Zou, Qun Niu, Li Pan, and Hefeng Wu
|
|
Weak-structure-aware visual object tracking with bottom-up and top-down context exploration
Liu Ning, Liu Chang, Wu Hefeng*, and Zhu Hengzheng
|