We propose a Universal Defence against backdoor attacks based on Clustering and Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural Network model is subject to a backdoor attack by inspecting the training dataset. CCA-UD first clusters the samples of the training set by means of density-based clustering. Then, it applies a novel strategy to detect the presence of poisoned clusters. The proposed strategy is based on a general misclassification behaviour observed when the features of a representative example of the analysed cluster are added to benign samples. The capability of inducing a misclassification error is a general characteristic of poisoned samples, hence the proposed defence is attack-agnostic. This marks a significant difference with respect to existing defences, that, either can defend against only some types of backdoor attacks, or are effective only when some conditions on the poisoning ratio or the kind of triggering signal used by the attacker are satisfied.
Experiments carried out on several classification tasks and network architectures, considering different types of backdoor attacks (with either clean or corrupted labels), and triggering signals, including both global and local triggering signals, as well as sample-specific and source-specific triggers, reveal that the proposed method is very effective to defend against backdoor attacks in all the cases, always outperforming the state of the art techniques.
An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance
Shanghai University(上海大学)
本文提出了一种新颖、有效、简单的端到端图像聚类自动编码算法:ICAE。该算法以PEDCC(Predefined Evenly-Distributed Class Centroids)为聚类中心,保证潜在特征的类间距离最大,并加入数据分布约束、数据增强约束、自动编码器重构约束和Sobel平滑约束,以提高聚类性能。具体来说,我们执行一对一的数据增强来学习更有效的特征。数据和增强数据被同时输入到自动编码器中以获得潜在特征和增强潜在特征,其相似性受到增强损失的约束。然后,利用最大平均差异距离(MMD),我们结合潜在特征和增强的潜在特征,使其分布接近PEDCC分布(类间均匀分布,类内Dirac分布),以进一步学习面向聚类的特征。同时,以原始输入图像和重建图像的均方误差作为重建约束,并利用Sobel平滑损失建立泛化约束,提高泛化能力。最后,在三个常用数据集MNIST,Fashion-MNIST,COIL 20上进行了广泛的实验。实验结果表明,该算法取得了迄今为止最好的聚类结果。此外,我们可以使用预定义的PEDCC类中心,以及解码器来清楚地生成每个类的样本。代码可以在https://github.com/zyWang-Power/Clustering下载!
A Holistic Method for Superquadric Fitting Using Unsupervised Clustering Analysis
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(数学科学国家重点实验室,数学与系统科学学院,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Robotics Institute, School of Mechanical Engineering and Automation, Beihang University(北京航空航天大学机械工程与自动化学院机器人研究所)
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);School of Computing, National University of Singapore(新加坡国立大学计算机学院)
Hefei University of Technology(合肥工业大学);University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);Kansai University(关西大学)
Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所 多模态人工智能系统国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Xiaomi Inc.(小米公司);State Key Laboratory of CNS/ATM, Beihang University(北京航空航天大学 CNS/ATM 国家重点实验室);College of Computer Science, Inner Mongolia University(内蒙古大学 计算机学院)
Towards Backdoor Attacks and Defense in Robust Machine Learning Models
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(卢森堡大学跨学科安全、可靠性与信任中心(SnT));Singapore University of Technology and Design(新加坡科技设计大学)
FLARE: Toward Universal Dataset Purification against Backdoor Attacks
School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院);School of Information Technology, Deakin University(德克萨斯大学信息学院);School of Information and Communication Technology, Griffith University(格里菲斯大学信息与通信技术学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
1 School of Cyber Science;Engineering, Wuhan University 0.3em 2 School of Computer Science, Wuhan University 0.3em 3 Institute for Math \& AI, Wuhan University