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:2606. 10099v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns about misuse such as plagiarism, misinformation, and automated influence operations, motivating the need for robust detectors.
By Rafael Rivera Soto, Barry Chen, Nicholas Andrews
arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.
By Omar Mahmoud, Aly M. Kassem, Thommen George Karimpanal, Buddhika Laknath Semage, Negar Rostamzadeh, Golnoosh Farnadi, Santu Rana
arXiv:2605.12890v2 Announce Type: replace-cross
Abstract: The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-writte...
By Luxu Liang, Xiang Li
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
By Gianluca Barmina, Peter Schneider-Kamp, Lukas Galke Poech
UniGuardian is a training‑free detector for large language models that jointly identifies prompt injection, backdoor, and adversarial attacks—collectively called Prompt Trigger Attacks (PTA). It measures how structured prompt perturbations shift the model’s output distribution and uses a single‑forward strategy to detect attacks while generating text in a shared batched forward pass. Experiments show that UniGuardian accurately and efficiently identifies trigger‑activated prompts in LLMs.
By Huawei Lin, Yingjie Lao, Tony Geng, Tan Yu, Weijie Zhao
arXiv:2606. 07313v1 Announce Type: cross Abstract: Detecting machine-generated text is especially difficult under distribution shift, such as transfer across domains, source models, and editing attacks.
By Mikhail Vishnyakov, Tatiana Gaintseva
arXiv:2608.21664v1 Announce Type: new
Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especiall...
By Marek Mateusz Kowalski, Joshua Fonseca Rivera, Uzay Macar, David Demitri Africa
arXiv:2606. 07696v1 Announce Type: cross Abstract: Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time.
By Kien Le, Thai Le
arXiv:2608.11025v2 Announce Type: replace
Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A...
By Clemens Vetter, David Kacz\'er, Lucie Flek, Florian Mai
The paper investigates how multimodal large language models are more susceptible to prompt injection when adversarial instructions are presented as text rather than as non-textual inputs like images. It proposes a training‑free defense that renders untrusted payloads into typographic images (or audio) before they reach the model, a method called Pictionary. Experiments on ten models and two benchmarks show that this approach significantly lowers attack success rates while maintaining normal functionality, and that fine‑tuning on image‑rendered instructions can further reduce the modality gap.
By Jie Zhang, Andrei Baroian, Jan N. van Rijn, Avital Shafran, Florian Tram\`{e}r
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal