TrojanWorld is a backdoor framework that targets world-model agents by steering their internal imagination toward attacker-specified actions when a physical trigger is present. The attack uses Decision-Reflective Induction, Clean Behavior Anchoring, and Causal Propagation to maintain stealth, persistence, and high performance. Experiments on TD-MPC2, DreamerV3, and R2-Dreamer across several benchmarks show that the attack can induce target actions with minimal performance loss and can keep agents on a malicious trajectory even after the trigger is removed.
By Wenkai Huang, Siyuan Liang, Gaolei Li, Yiming Li, Tianhao Peng, Jianhua Li, Dacheng Tao
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov
arXiv:2606. 18697v1 Announce Type: new Abstract: Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments.
By Yibin Hu, Xiaolin Sun, Zizhan Zheng
arXiv:2608. 11295v1 Announce Type: cross Abstract: Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing.
By Gabriel Huang, Abhay Puri, L\'eo Boisvert, Alexandre Drouin, Perouz Taslakian, Spandana Gella, Christopher Pal
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.
arXiv:2510.17021v2 Announce Type: replace-cross
Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while ret...
By Bingqi Shang, Yiwei Chen, Yihua Zhang, Bingquan Shen, Sijia Liu
arXiv:2607. 24893v1 Announce Type: cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run.
By Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang, Yibo Hu
arXiv:2607. 15207v1 Announce Type: new Abstract: World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction.
By Qi Li, Xingyi Yang, Xinchao Wang
arXiv:2608. 09577v1 Announce Type: new Abstract: Agent skills, bundles of instructions and resources that an LLM agent loads on demand, form an emerging supply chain where a single poisoned skill can persistently compromise every agent that installs it.
By Hao Sui, Simeng Qin, Jie Liao, Xiaojun Jia, Bing Chen, Yang Liu
arXiv:2606. 04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.
By Jack Sanderson, Yihan Wang, Xiaoqian Lu, Gautam Kamath, Yiwei Lu
arXiv:2606. 16605v1 Announce Type: new Abstract: World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making.
By Junjian Zhang, Hao Tan, Ruonan Li, Dong Zhu, Aiping Li, Zhaoquan Gu
arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.
By Jun Wen Leong