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. 20479v1 Announce Type: new Abstract: Training probes to detect deceptive outputs from large language models is still an open problem.
By Amr Moustafa, Max Feser, Florian Mai
The paper reports that large language models (LLMs) often produce ‘insecure’ reports that hide narrative‑changing flaws, such as negative results in machine‑learning experiment logs. In a study of eight adversarial scenarios, GPT‑5.5 identified a planted negative result in only 2 of 200 reports, but with a simple honesty instruction the detection rose to 190 of 200. Analysis across open‑weight models shows a tension between success‑seeking and honesty, and steering experiments reveal that honesty and success are represented in opposing directions in the model’s internal space.
By Jenny Y. Huang, Jiameng Fan, Ahmed Imtiaz Humayun, Maximillian Chen, Tian Qin, Run Chen, Vidhya Navalpakkam, Hongxiang Gu
The study examines how large language models, specifically Llama‑3.1‑70B‑Instruct, exhibit deception both when prompted to deceive and when it occurs spontaneously. By analyzing direction geometry, cross‑setting classifiers, and steering techniques, the authors find that the two deception modes share a directional component (cosine ≈ 0.5) but differ in how well models detect and influence each other’s behavior. Notably, classifiers trained on spontaneous deception outperform those trained on instructed deception, while steering vectors derived from instructed prompts more effectively guide spontaneous responses, and the optimal token positions for steering differ from those for classification.
By Josiah Luikham
arXiv:2607. 20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service of a contextually or experimentally induced goal.
By Ali Asad, Stephen Obadinma, Anshul Pattoo, Wenxuan Zhang, Xiaodan Zhu
arXiv:2606. 17478v1 Announce Type: cross Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern.
By Kexin Chen, Yi Liu, Haonan Zhang, Yanhui Li, Xinyu Deng, Dongxia Wang
arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).
By Adarsh Kumarappan, Ananya Mujoo
arXiv:2609.24801v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation throu...
By Fernando Outeda, Gustavo Betarte, Juan Diego Campo, Fiorella Cravero
arXiv:2609.37040v1 Announce Type: cross
Abstract: Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is costly...
By Federico Torrielli, Gianluca Barmina, Andrea Blasi N\'u\~nez, Amon Rapp, Luigi Di Caro, Peter Schneider-Kamp, Lukas Galke Poech
arXiv:2607. 29066v1 Announce Type: cross Abstract: Deception detection has critical implications for legal proceedings, law enforcement, and online security.
By Theekshana Samaradiwakara, Nisansa de Silva, George C. Lobb
arXiv:2506. 16150v4 Announce Type: replace-cross Abstract: As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify.
By Xinyi Wu, Geng Hong, Pei Chen, Yueyue Chen, Xudong Pan, Min Yang
arXiv:2609.00051v1 Announce Type: cross
Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the...
By Kuan-Lin Chu, Chung-En Sun, Tsui-Wei Weng