paper-with-me

Papers

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

2025-06-06 · Zhilong Wang, Neha Nagaraja, Lan Zhang, Hayretdin Bahsi, Pawan Patil, Peng Liu

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. Traditional defenses like input sanitization, guard models, and guardrails are either cumbersome or ineffective. In this paper, we propose a novel, lightweight defense mechanism called Polymorphic Prompt Assembling (PPA), which protects against prompt injection with near-zero overhead. The approach is based on the insight that prompt injection requires guessing and breaking the structure of the system prompt. By dynamically varying the structure of system prompts, PPA prevents attackers from predicting the prompt structure, thereby enhancing security without compromising performance. We conducted experiments to evaluate the effectiveness of PPA against existing attacks and compared it with other defense methods.

📄 PDF Abstract BibTeX arXiv:2506.05739

Code (1)

zhilongwang/llmagentprotector 공식 구현

Methods 이 논문이 사용한 방법론

customer support 설명 없음

Similar Papers 제목 키워드 기반

BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents

2025-11-25 · Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley, Jerry Ma 외 arxiv

The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack…

Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails

2025-04-15 · William Hackett, Lewis Birch, Stefan Trawicki, Neeraj Suri 외

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LL…

AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents

2026-06-13 · Xinhang Ma, Taoran Li, Chaowei Xiao, Zhiyuan Yu 외 arxiv

Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work have proposed a variety of defensive approaches against IPI. These can be grouped into three broad categories…

PromptArmor: Simple yet Effective Prompt Injection Defenses

2025-07-21 · Tianneng Shi, Kaijie Zhu, Zhun Wang, Yuqi Jia 외 arxiv

Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specifi…

Detecting Prompt Injection Attacks Against Application Using Classifiers

2025-12-14 · Safwan Shaheer, G. M. Refatul Islam, Mohammad Rafid Hamid, Md. Abrar Faiaz Khan 외 arxiv

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Pl…