Backdoor attacks severely threaten large-scale AI models. When model owners delegate training to external compute providers within a decentralized training paradigm, adversaries can craft stealthy, low-frequency triggers to inject malicious behavior while evading standard audits. Traditionally, detecting these attacks requires a full re-computation of the training steps--a prohibitive overhead that directly contradicts the owner's resource constraints. To address this, we investigate the resilience of continuous optimization dynamics under Byzantine perturbations, where adversaries are forced to compete against a continuous influx of honest updates. Under a threat model where an adversary compromises f out of n total trainers, we quantify the minimum auditing overhead required by the model owner to probabilistically bound the attack success rate. We formalize this injection-absorption dynamic as a Discrete-Time Markov Chain (DTMC). Using this framework, we prove that the success probability of any bounded adversary asymptotically collapses to zero under a defense strategy combining natural absorption, a randomized scheduler, and lazy verification oracle. Empirical results demonstrate significant backdoor suppression with zero utility degradation even when invoking the verification oracle on merely 10% of the total training steps. This approach yields a provably sound and computationally efficient defense for safety-critical AI.
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
University of Maryland(马里兰大学);Oregon State University(俄勒冈州立大学);ELLIS Institute Tübingen(埃利斯研究所蒂宾根分部);MPI Intelligent Systems(马克斯·普朗克智能系统研究所);Google DeepMind(谷歌DeepMind)
Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning
Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education(高可信软件技术重点实验室(北京大学));School of Computer Science, Peking University(北京大学计算机学院);Zhongguancun Laboratory(中关村实验室)
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
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);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));School of Cyber Science and Engineering, Xi’an Jiaotong University(西安交通大学网络空间安全学院)
Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
Nanjing University of Science and Technology(南京理工大学);Data61, CSIRO(澳大利亚联邦科学与工业研究组织 Data61);The University of Adelaide(阿德莱德大学);The University of Queensland(昆士兰大学);Hunan University(湖南大学);Sungkyunkwan University(成均馆大学)
Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
University of Science and Technology of China(中国科学技术大学);Nanyang Technological University(南洋理工大学);United Arab Emirates University(阿拉伯联合酋长国大学);University of California San Diego(加州大学圣地亚哥分校);Abel AI;National University of Singapore(新加坡国立大学);Squirrel Ai Learning
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
CSIRO’s Data61(联邦科学与工业研究组织数据61研究所);University of Technology Sydney(悉尼科技大学);The University of Western Australia(西澳大学);Fudan University(复旦大学);Nanjing University of Science and Technology(南京理工大学);The University of Adelaide(阿德莱德大学)
Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);University of Cambridge(剑桥大学);University of Macau(澳门大学)
CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
Deep Interdisciplinary Intelligence Lab HKUST(GZ)(深 interdisciplinary 智能实验室,香港科技大学(广州));HKUST(GZ)(香港科技大学(广州));KAUST(科威特大学);Central South University(中南大学);University of Macau(澳门大学);Institute of Deep Perception Technology, JITRI(深度感知技术研究所,JITRI)
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Beijing University of Posts and Telecommunications(北京邮电大学);University at Buffalo, State University of New York(纽约州立大学布法罗分校)