paper-with-me

Papers

Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications

2024-01-15 · Xuchen Suo

The critical challenge of prompt injection attacks in Large Language Models (LLMs) integrated applications, a growing concern in the Artificial Intelligence (AI) field. Such attacks, which manipulate LLMs through natural language inputs, pose a significant threat to the security of these applications. Traditional defense strategies, including output and input filtering, as well as delimiter use, have proven inadequate. This paper introduces the 'Signed-Prompt' method as a novel solution. The study involves signing sensitive instructions within command segments by authorized users, enabling the LLM to discern trusted instruction sources. The paper presents a comprehensive analysis of prompt injection attack patterns, followed by a detailed explanation of the Signed-Prompt concept, including its basic architecture and implementation through both prompt engineering and fine-tuning of LLMs. Experiments demonstrate the effectiveness of the Signed-Prompt method, showing substantial resistance to various types of prompt injection attacks, thus validating its potential as a robust defense strategy in AI security.

📄 PDF Abstract BibTeX arXiv:2401.07612

Code (0)

등록된 구현이 없습니다.

Tasks

input filteringPrompt Engineering

Similar Papers 제목 키워드 기반

SecInfer: Preventing Prompt Injection via Inference-time Scaling

2025-09-29 · Yupei Liu, Yanting Wang, Yuqi Jia, Jinyuan Jia 외 arxiv

Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve …

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization

2025-11-13 · Runpeng Geng, Yanting Wang, Chenlong Yin, Minhao Cheng 외 arxiv

Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existing prompt injection defenses are designed…

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt

2025-06-06 · Zhilong Wang, Neha Nagaraja, Lan Zhang, Hayretdin Bahsi 외

LLM agents are widely used as agents for customer support, content generation, and code assistance. However, they are vulnerable to prompt injection attacks, where adversarial inputs manipulate the model's behavior. Trad…

Prompt Fencing: A Cryptographic Approach to Establishing Security Boundaries in Large Language Model Prompts

2025-11-24 · Steven Peh arxiv

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that appl…

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models

2025-02-18 · Huawei Lin, Yingjie Lao, Tong Geng, Tan Yu 외

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from tradi…

Text Generation