Graph Convolutional Networks (GCNs) have shown excellent performance in dealing with various graph structures such as node classification, graph classification and other tasks. However,recent studies have shown that GCNs are vulnerable to a novel threat known as backdoor attacks. However, all existing backdoor attacks in the graph domain require modifying the training samples to accomplish the backdoor injection, which may not be practical in many realistic scenarios where adversaries have no access to modify the training samples and may leads to the backdoor attack being detected easily. In order to explore the backdoor vulnerability of GCNs and create a more practical and stealthy backdoor attack method, this paper proposes a clean-graph backdoor attack against GCNs (CBAG) in the node classification task,which only poisons the training labels without any modification to the training samples, revealing that GCNs have this security vulnerability. Specifically, CBAG designs a new trigger exploration method to find important feature dimensions as the trigger patterns to improve the attack performance. By poisoning the training labels, a hidden backdoor is injected into the GCNs model. Experimental results show that our clean graph backdoor can achieve 99% attack success rate while maintaining the functionality of the GCNs model on benign samples.
Anti-Backdoor Learning: Training Clean Models on Poisoned Data
Xidian University(西安电子科技大学);University of Copenhagen(哥本哈根大学);Sony AI(索尼人工智能);University of Illinois at Urbana–Champaign(伊利诺伊大学厄巴纳-香槟分校);Deakin University(迪肯大学)
CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack
School of Computer Science and Technology, Zhejiang Gongshang University(浙江工商大学计算机科学与技术学院);School of Mathematical and Computational Sciences, Massey University(梅西大学数学与计算科学学院)
TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning
School of Control Science and Engineering, Shandong University, Jinan, China(控制科学与工程学院,山东大学,济南,中国);Key Laboratory of Industrial Intelligent Systems, Shandong Province, China(山东省工业智能系统重点实验室,中国)
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
Peking University(北京大学)
自然语言处理(Natural Language Processing,NLP)模型易受后门攻击的攻击,这是NLP模型面临的一个新的威胁。现有的NLP模型在线后门防御方法只关注输入或输出层面的异常,仍然存在易受自适应攻击和计算代价高的问题。在这项工作中,我们采取的第一步,在中间特征水平上研究文本中毒样本的去隐藏,并提出了一种基于特征的有效的在线防御方法。通过对现有攻击方法的大量实验,我们发现中毒样本在中毒NLP模型的中间特征空间中远离干净样本。出于这一观察,我们设计了一个基于距离的异常分数(DAN)区分中毒的样本从干净的样本在功能级别。在情感分析和攻击检测任务上的实验证明了DAN的优越性,因为它在防御性能方面大大超过现有的在线防御方法,并且具有较低的推理成本。此外,我们还证明了DAN也能抵抗基于特征级正则化的自适应攻击。我们的代码可在https://github.com/lancopku/DAN上获得。
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features
School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院);Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network(深圳市人群智能赋能低碳能源网络重点实验室)
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
Laboratory Of Intelligent Collaborative Computing, University of Electronic Science and Technology of China(智能协同计算实验室,电子科技大学);School of Computer Science and Technology, Xinjiang University(计算机科学与技术学院,新疆大学);School of Computer Science and Engineering, University of Electronic Science and Technology of China(计算机科学与工程学院,电子科技大学);School of Computer Science, Fudan University(计算机科学学院,复旦大学)
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Nanyang Technological University(南洋理工大学);Hong Kong University of Science and Technology(香港科技大学);Jinan University(暨南大学);Sony Research(索尼研究院);Zhejiang University(浙江大学);Beijing Institute of Technology(北京理工大学)
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
University of Alberta(阿尔伯塔大学);Michigan State University(密歇根州立大学);Illinois Institute of Technology(伊利诺伊理工学院);DSO National Laboratories(新加坡国防科技局国家实验室);MIT-IBM Watson AI Lab, IBM Research(IBM研究院MIT-IBM沃森人工智能实验室)
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)
Neurotoxin: Durable Backdoors in Federated Learning
Southeast University(东南大学);Princeton University(普林斯顿大学);University of California at Berkeley(加州大学伯克利分校);International Computer Science Institute(国际计算机科学研究所)
由于其分散的性质,联邦学习(FL)系统在训练过程中对对抗性后门攻击具有固有的脆弱性。在这种类型的攻击中,攻击者的目标是使用中毒更新将所谓的后门植入到学习模型中,以便在测试时,模型的输出可以固定为特定输入的给定目标。(As一个简单的玩具示例,如果用户将“people from New York”键入到使用后门下一单词预测模型的移动键盘应用中,则该模型可以将句子自动完成为“people from New York are rude”)。先前的工作已经表明,后门可以插入到FL模型中,但是这些后门通常不耐用,即,在攻击者停止上载中毒更新之后,它们不会保留在模型中。因此,由于训练通常在生产FL系统中逐步继续,因此插入的后门可能无法存活直到部署。在这里,我们提出了神经毒素,一个简单的一行修改现有的后门攻击,通过攻击参数,在训练过程中变化较小的幅度。我们对十个自然语言处理和计算机视觉任务进行了详尽的评估,我们发现我们可以将最先进的后门的耐久性提高一倍。
Triggerless Backdoor Attack for NLP Tasks with Clean Labels
Zhejiang University(浙江大学);Nanyang Technological University(南洋理工大学);Shanghai Institute for Advanced Study of Zhejiang University(浙江大学上海高等研究院);Shanghai AI Laboratory(上海人工智能实验室);Chongqing University(重庆大学);Peng Cheng Laboratory(鹏城实验室);Peking University(北京大学)
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
University of Science and Technology of China(中国科学技术大学);Beijing University of Aeronautics and Astronautics(北京航空航天大学);Nanyang Technological University(南洋理工大学);Southwest Jiaotong University(西南交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
Xidian University(西安电子科技大学);The University of Melbourne(墨尔本大学);Ant Group(蚂蚁集团);University of Illinois at Urbana–Champaign(伊利诺伊大学厄巴纳-香槟分校);Deakin University(迪肯大学)