TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

Large Language Models (LLMs) are progressively being utilized as machine learning services and interface tools for various applications. However, the security implications of LLMs, particularly in relation to adversarial and Trojan attacks, remain insufficiently examined. In this paper, we propose TrojLLM, an automatic and black-box framework to effectively generate universal and stealthy triggers. When these triggers are incorporated into the input data, the LLMs' outputs can be maliciously manipulated. Moreover, the framework also supports embedding Trojans within discrete prompts, enhancing the overall effectiveness and precision of the triggers' attacks. Specifically, we propose a trigger discovery algorithm for generating universal triggers for various inputs by querying victim LLMbased APIs using few-shot data samples. Furthermore, we introduce a novel progressive Trojan poisoning algorithm designed to generate poisoned prompts that retain efficacy and transferability across a diverse range of models. Our experiments and results demonstrate TrojLLM's capacity to effectively insert Trojans into text prompts in real-world black-box LLM APIs including GPT-3.5 and GPT-4, while maintaining exceptional performance on clean test sets. Our work sheds light on the potential security risks in current models and offers a potential defensive approach. The source code of TrojLLM is available at https://github.com/UCF-ML-Research/TrojLLM . Attaining high-performance prompts typically demands considerable domain expertise and extensive validation sets; concurrently, manually crafted prompts have been identified as sub-optimal, leading to inconsistent performance [8, 9] . Consequently, the automatic search and generation of prompts have garnered significant research interest [4, 10] . One prevalent approach involves tuning soft prompts (i.e., continuous embedding vectors) as they can readily accommodate gradient descent [5, 11] . 37th Conference on Neural Information Processing Systems (NeurIPS 2023).