LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata used to describe those tools creates a prompt-injection surface. Within this established tool-poisoning surface, we study Log-To-Leak, an additive post-hoc logging attack that induces a separate attacker-controlled call after the final legitimate call. Its payload targets the user query, MCP server name, server response, and agent response. We operationalize the injected directive through Trigger, Tool Binding, Justification, and Pressure, and separately measure call success, payload fidelity, and preservation of legitimate behavior. We evaluate five MCP servers and four LLM agents using five metrics spanning effectiveness, utility, and efficiency. Across 18 model-server pairs with valid tool execution, Log-To-Leak achieves an attack success rate (ASR) of 62.64-100% and conditional logging accuracy (LA) of 76.55-95.64%; 16 pairs have absolute target-task completion changes of at most 6.63 percentage points. Three evaluated defenses leave residual ASR above 55% on GitHub MCP with GPT-4o, while an instruction detector flags 85.53% of benign descriptions. These results show that successful task completion can coexist with unauthorized post-hoc disclosure and motivate host-controlled authorization for secondary tool calls.
Yuepeng Hu, Zhengyuan Jiang Duke University, Mengyuan Li, Osama Ahmed Facebook, Zhicong Huang Ant Group, Cheng Hong Ant Group, Neil Zhenqiang Gong
Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection methods have two main limitations: (1) they embed signals into the base model before release, which is infeasible for already published models, or (2) they compare outputs across models using hand-crafted or random prompts, which are not robust to post-processing. In this work, we propose LLMPrint, a novel detection framework that constructs fingerprints by exploiting LLMs’ inherent vulnerability to prompt injection. Our key insight is that by optimizing fingerprint prompts to enforce consistent token preferences, we can obtain fingerprints that are both unique to the base model and robust to post-processing. We further develop a unified verification procedure that applies to both gray-box and black-box settings, with statistical guarantees. We evaluate LLMPrint on five base models and around 700 post-trained or quantized variants. Our results show that LLMPrint achieves high true positive rates while keeping false positive rates near zero. The code is publicly available at https://github.com/hifi-hyp/ACL-LLMPrint.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zedian Shao, Hongbin Liu Google, Yuepeng Hu, Neil Zhenqiang Gong
Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but also raising critical safety and societal concerns. In particular, these models may be misused to extract sensitive information from personal images, such as identifying individuals or revealing locations. In this work, we propose ImageProtector, a method designed to protect images from unauthorized analysis by MLLMs. Before an image is shared online, ImageProtector embeds a carefully crafted, nearly imperceptible perturbation that acts as a visual prompt injection attack on MLLMs. Consequently, when a malicious actor downloads and queries a protected image, the MLLM is consistently misled into generating a refusal response such as “I’m sorry, I can’t help with that request.” We empirically demonstrate the effectiveness of ImageProtector across six MLLMs and four datasets. Additionally, we evaluate three potential countermeasures, Gaussian noise, DiffPure, and adversarial training, and show that while they partially mitigate the impact of ImageProtector, they simultaneously degrade model accuracy and/or efficiency.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表