DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models

Computer Science > Cryptography and Security [Submitted on 15 May 2026] DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models Ye Sun, Xin Wang, Jiaming Zhang, Yifeng Gao, Yixu Wang, Yifan Ding, Qixian Zhang, Henghui Ding, Xingjun Ma, Yu-Gang Jiang While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single, predefined objectives, tightly coupling each attack to a specific model or task, which restricts their scalability and flexibility in real-world scenarios. In this work, we present DarkLLM, a novel attack framework that trains an LLM to translate natural-language attack instructions into latent attack vectors, which are then decoded into visual adversarial perturbations. By leveraging natural-language instruction tuning, DarkLLM not only unifies targeted, untargeted, segmentation, and multi-model attacks within a single framework, but also achieves flexible and controllable adversarial generation, enabling each instruction to produce a perturbation that induces desired behaviors across heterogeneous models. Through extensive experiments across 4 tasks, 13 datasets, and 15 models, we demonstrate that DarkLLM with only 1B parameters can follow attacker instructions and generate highly effective attacks against CLIP, SAM, and frontier LLMs, revealing a systemic vulnerability in modern foundation models. Comments: 23 pages, 13 figures Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) Cite as: arXiv:2605.18868 [cs.CR]   (or arXiv:2605.18868v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.18868 Focus to learn more Submission history From: Ye Sun [view email] [v1] Fri, 15 May 2026 12:28:16 UTC (7,195 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.AI cs.CV cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)