The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
By Md. Hasib Ur Rahman
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
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.
Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown backdoors may exist in a model.
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.
arXiv:2607. 15267v1 Announce Type: new Abstract: Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate.
By Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith, David Kohlbrenner, Kyle Lo
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
By Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang
arXiv:2610.03124v1 Announce Type: cross
Abstract: Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enfor...
By Toluwani Aremu, Manit Baser, Mohan Gurusamy, Nils Lukas, Dinil Mon Divakaran
arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.
By Shawn Li, Yue Zhao
The paper introduces the Cancerous Backdoor Attack, a novel backdoor technique for large language models that activates gradually through multiple hidden stages rather than a single trigger-response. It uses invisible tokens to embed intermediate stages into the model’s reasoning process and a stage controller to monitor the attack’s progression during inference. Experiments on various reasoning datasets show that this method consistently corrupts model outputs over time and outperforms existing backdoor baselines.
By Tahmid Imtiaz Imu, Emama Nahid, Prodipta Sen Amartya, Ahsanul Jobayer, Yutong Song, Jiang Wu, Pengfei Zhang, Honghui Xu
arXiv:2606. 13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences.
By Zihao Wang, Yiming Li, Yutong Wu, Zheyu Liu, Kangjie Chen, Fok Kar Wai, Pin-Yu Chen, Vrizlynn L. L. Thing, Bo Li, Dacheng Tao, Tianwei Zhang
arXiv:2606. 09700v1 Announce Type: cross Abstract: Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content.
By Qin Yang, Lu Malloy, Joshua Lee, Xiaohan Chang, Meisam Mohammady, Doowon Kim, Yuan Hong