Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of updating world models from collected experience creates a training-time attack surface: adversarially poisoned fine-tuning trajectories can manipulate the learned dynamics and thereby corrupt downstream planning. In this paper, we propose SWAAP, the first two-stage data poisoning framework for learned world models. In the first stage, SWAAP identifies a harmful target world model that induces low-return behavior under planning while remaining close to clean dynamics, using first-order bilevel optimization enabled by a transition-gradient theorem. In the second stage, SWAAP realizes this target through stealth-constrained gradient matching, modifying only a limited fraction of fine-tuning transition targets so that the induced training gradients steer the victim model toward the adversarial target, while a prediction-error regularizer encourages the poisoned targets to remain close to the world model's natural approximation error. To assess attack stealthiness, we evaluate defenses and detectability across three stages of the poisoning pipeline: pre-training detection of poisoned transitions, robust training during fine-tuning, and test-time monitoring of the resulting world model. Across diverse continuous-control tasks, SWAAP causes substantial performance degradation while keeping poisoned transitions close to clean data and evading the evaluated non-adaptive residual/CUSUM/TRIM-style defenses. These results reveal a practical vulnerability in world-model adaptation pipelines and highlight the need for robustness methods that protect both world-model training data and learned dynamics.
Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
IBM Research Europe, Portal, First Floor Trinity Business School, Trinity College Dublin(IBM欧洲研究院,波特尔大楼,特里尼蒂商务学校,特里尼蒂学院都柏林);Imperial College London, South Kensington Campus(伦敦帝国理工学院,南肯辛顿校区);Universidad de Alcalá de Henares, Escuela Politécnica Superior(阿尔卡萨大学,工程技术学院);Defence Science and Technology Laboratory (DSTL), Porton Down, Salisbury(国防科学与技术实验室(DSTL),波特恩道,萨里)
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
University of Maryland, College Park(马里兰大学帕克分校);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Salesforce Research(Salesforce研究院);Apple(苹果公司);Netflix(网飞公司);Eyeline Studios(Eyeline工作室);University of Waterloo(滑铁卢大学)
State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
Laboratory Of Intelligent Collaborative Computing, University of Electronic Science and Technology of China(智能协同计算实验室,电子科学与技术大学);National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China(无线通信国家重点实验室,电子科学与技术大学);School of Computer Science and Engineering, University of Electronic Science and Technology of China(计算机科学与工程学院,电子科学与技术大学);College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(计算机科学与技术学院,南京航空航天大学);College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)
Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
Department of Electronics Engineering, Tsinghua University, Beijing, China(清华大学电子工程系);College of AI, Tsinghua University, Beijing, China(清华大学人工智能学院);Beijing National Research Center for Information Science and Technology, Beijing, China(北京信息科学国家研究中心)
Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
CortAIx Labs, Thales Deutschland(Thales Deutschland);Grey Solutions;University of Osnabrück(奥斯纳布吕克大学);Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院);Ulm University(乌尔姆大学)
Learning to Poison Large Language Models for Downstream Manipulation
Department of Computer Science, Wayne State University(韦恩州立大学计算机科学系);Computer Science and Engineering Department, Oakland University(奥克兰大学计算机科学与工程系);College of Innovation and Technology, University of Michigan-Flint(密歇根大学弗林特分校创新与技术学院)
Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
College of Engineering and Computer Science, VinUniversity(VinUniversity工程与计算机科学学院);CSIRO’s Data61(澳大利亚联邦科学与工业研究组织Data61);Johns Hopkins University(约翰斯·霍普金斯大学);Vietnam National University(越南国立大学)
Exploring Model Dynamics for Accumulative Poisoning Discovery
Hong Kong Baptist University(香港浸会大学);Alibaba Group(阿里巴巴集团);Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);The University of Sydney(悉尼大学)
Certified Robustness to Data Poisoning in Gradient-Based Training
Department of Computing, Imperial College London, United Kingdom(帝国理工学院伦敦分校计算机系);Department of Computer Science, ETH Zurich, Switzerland(苏黎世联邦理工学院计算机科学系);LogicStar.ai, Switzerland(LogicStar.ai公司);The Alan Turing Institute, United Kingdom(艾伦·图灵研究所)
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
School of Electronic Engineering(电子工程学院);Beijing University of Posts and Telecommunications(北京邮电大学);Centre for Frontier AI Research (CFAR)(前沿人工智能研究中心);Institute of High Performance Computing (IHPC)(高性能计算研究所);Agency for Science Technology and Research (A*STAR)(新加坡科技研究局);School of Information and Communication(信息与通信学院)
Poisoning the corpora of protein design systems during pre-training and retrieval
The University of Texas at Austin(德克萨斯大学奥斯汀分校);BSRC “Alexander Fleming,”(亚历山大·弗莱明基础科学研究中心);Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(穆罕默德·本·扎耶德人工智能大学)