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

ArXi:2605.18868v1 Announce Type: cross 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.