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...
By Yan Zhan, Yunze Song, Mengkai Hou, Wanting Zhang, Shaobo Liu, Zhijun Gao
arXiv:2510. 10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs).
By Wentian Zhu, Zhen Xiang, Wei Niu, Le Guan
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.
By Joshua Penman
The paper introduces an attack that reconstructs text generated by locally hosted large language models by monitoring CPU cache activity during detokenization. It uses Flush+Reload on shared tokenizer code to time decoding, then Prime+Probe to capture token‑dependent cache traces, followed by a clustering‑and‑language‑model pipeline to recover the output text. The method is evaluated across various datasets, hardware, inference frameworks, and model families, successfully retrieving semantically accurate outputs from real‑world local LLM deployments, including agentic systems.
By Roy Weiss, Benyamin Konstantinov, Eitam Sheetrit, Tomer Simon, Yisroel Mirsky
Repeat-After-Me is a black-box adaptive visual prompt injection technique that can reveal personally identifiable information or trigger malicious tool calls in both open-weight and commercial vision‑language models, achieving attack success rates above 80% on Qwen3.6‑27B and 47% on GPT‑5.5. The method works even when the benign user prompt is unrelated to the injected task and does not explicitly authorize it, and it retains significant effectiveness when transferred across models or optimized on surrogate systems. In a real‑world OpenClaw Discord deployment, a minimally injected image can overwrite TOOLS.md, enabling remote code execution and secret exfiltration.
By Sizhe Chen, Yu-Lin Tsai, Ivan Evtimov, Kamalika Chaudhuri, Raluca Ada Popa, David Wagner, Arman Zharmagambetov
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
By Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini, Adrian Robert Minut, Iacopo Masi, Emanuele Rodol\`a