arXiv:2606. 18120v1 Announce Type: cross Abstract: Large language model applications build prompts from templates, and Handlebars is a widely used templating engine and the default prompt-template format in Microsoft Semantic Kernel.
arXiv:2609.35932v1 Announce Type: cross Abstract: Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged templat...
The paper introduces Semantic Overlays, a steering technique that adds non‑textual annotations to a language model’s input by applying learned adapters at specific prefill positions. These overlays create an out‑of‑band channel that encodes span identity and complex semantics, enabling the model to interpret marked text differently—such as rewriting code in a specified language or ignoring executable instructions. Experiments show that Semantic Overlays dramatically reduce prompt‑injection success rates while preserving model utility and readability of marked spans.
The paper critiques current encoded‑prompt safety benchmarks that focus only on harmful requests, showing that such tests can misrepresent a model’s safety. By evaluating the benign arm under the same encoding, the authors reveal a substantial drop in the harm gap—sometimes to zero—indicating that the encoding masks true safety deficiencies. Across multiple large models and training pipelines, they document that the encoding can either hide or falsely inflate safety metrics, and they identify twelve specific instrument defects that contribute to these misleading results.
The paper examines how open‑weight language models expose the control tokens used in chat templates, allowing attackers to forge turn boundaries that the model treats as legitimate. An audit of 256 deployed tokenizers shows all are vulnerable, and the commonly recommended flag fails to protect 56.6% of cases. The authors introduce nameless tokenization, which removes surface strings for control identifiers while preserving their internal representation, achieving identical token streams on clean data and significantly improving accuracy on delimiter‑bearing text.
arXiv:2607. 05744v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools.
arXiv:2601. 13359v3 Announce Type: replace-cross Abstract: Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.
arXiv:2503. 24191v4 Announce Type: replace-cross Abstract: Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers.
arXiv:2510.17904v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them par...
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that...
arXiv:2606. 05609v1 Announce Type: cross Abstract: As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical.
The paper introduces Paraesthesia, a dynamic backdoor attack that uses emotionally styled inputs as triggers for large language models. By mapping target emotions into a valence–arousal space and rewriting a small subset of clean samples, the attack achieves over 98% success while minimally affecting clean performance. Experiments on four major LLMs show that the trigger cannot be fully explained by token-level cues and remains robust against several filtering and mitigation techniques.
arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.