System Prompt Extraction Attacks and Defenses in Large Language Models

• URL: http://arxiv.org/abs/2505.23817v1
• Date: Tue, 27 May 2025 21:36:27 GMT
• Title: System Prompt Extraction Attacks and Defenses in Large Language Models
• Authors: Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu,
• Abstract summary: System prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation.<n>Recent studies have shown that LLM system prompts are highly susceptible to extraction attacks through meticulously designed queries.<n>Despite the growing threat, there is a lack of systematic studies of system prompt extraction attacks and defenses.
• Score: 2.6986500640871482
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that LLM system prompts are highly susceptible to extraction attacks through meticulously designed queries, raising significant privacy and security concerns. Despite the growing threat, there is a lack of systematic studies of system prompt extraction attacks and defenses. In this paper, we present a comprehensive framework, SPE-LLM, to systematically evaluate System Prompt Extraction attacks and defenses in LLMs. First, we design a set of novel adversarial queries that effectively extract system prompts in state-of-the-art (SOTA) LLMs, demonstrating the severe risks of LLM system prompt extraction attacks. Second, we propose three defense techniques to mitigate system prompt extraction attacks in LLMs, providing practical solutions for secure LLM deployments. Third, we introduce a set of rigorous evaluation metrics to accurately quantify the severity of system prompt extraction attacks in LLMs and conduct comprehensive experiments across multiple benchmark datasets, which validates the efficacy of our proposed SPE-LLM framework.

Related papers

• Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems [18.039444159491733]
  Large Language Models (LLMs) deployed in enterprise settings face novel security challenges.<n>One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually extract confidential data.<n>We present a comprehensive study of multi-stage prompt inference attacks in an enterprise LLM context.
  arXiv  Detail & Related papers  (2025-07-21T13:38:12Z)
• System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection [13.175123810033119]
  Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities.<n>Existing studies mainly focus on threats arising from user prompts, while the security of system prompts remains largely overlooked.<n>We introduce system prompt poisoning, a new attack vector against LLMs that, unlike traditional user prompt injection, poisons system prompts hence persistently impacts all subsequent user interactions and model responses.
  arXiv  Detail & Related papers  (2025-05-10T02:31:26Z)
• Attention Tracker: Detecting Prompt Injection Attacks in LLMs [62.247841717696765]
  Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks.<n>We introduce the concept of the distraction effect, where specific attention heads shift focus from the original instruction to the injected instruction.<n>We propose Attention Tracker, a training-free detection method that tracks attention patterns on instruction to detect prompt injection attacks.
  arXiv  Detail & Related papers  (2024-11-01T04:05:59Z)
• Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs) [17.670925982912312]
  Red-teaming is a technique for identifying vulnerabilities in large language models (LLM)<n>This paper presents a detailed threat model and provides a systematization of knowledge (SoK) of red-teaming attacks on LLMs.
  arXiv  Detail & Related papers  (2024-07-20T17:05:04Z)
• Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems [27.316115171846953]
  Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied AI.<n>LLMs are fine-tuned to leverage their inherent common sense and reasoning abilities while being tailored to specific applications.<n>This fine-tuning process introduces considerable safety and security vulnerabilities, especially in safety-critical cyber-physical systems.
  arXiv  Detail & Related papers  (2024-05-27T17:59:43Z)
• Prompt Leakage effect and defense strategies for multi-turn LLM interactions [95.33778028192593]
  Leakage of system prompts may compromise intellectual property and act as adversarial reconnaissance for an attacker. We design a unique threat model which leverages the LLM sycophancy effect and elevates the average attack success rate (ASR) from 17.7% to 86.2% in a multi-turn setting. We measure the mitigation effect of 7 black-box defense strategies, along with finetuning an open-source model to defend against leakage attempts.
  arXiv  Detail & Related papers  (2024-04-24T23:39:58Z)
• AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting [54.931241667414184]
  We propose textbfAdaptive textbfShield Prompting, which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks. Our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks.
  arXiv  Detail & Related papers  (2024-03-14T15:57:13Z)
• Stealthy Attack on Large Language Model based Recommendation [24.51398285321322]
  Large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS) In this work, we reveal that the introduction of LLMs into recommendation models presents new security vulnerabilities due to their emphasis on the textual content of items. We demonstrate that attackers can significantly boost an item's exposure by merely altering its textual content during the testing phase.
  arXiv  Detail & Related papers  (2024-02-18T16:51:02Z)
• LoRec: Large Language Model for Robust Sequential Recommendation against Poisoning Attacks [60.719158008403376]
  Our research focuses on the capabilities of Large Language Models (LLMs) in the detection of unknown fraudulent activities within recommender systems.<n>We propose LoRec, an advanced framework that employs LLM-Enhanced to strengthen the robustness of sequential recommender systems.<n>Our comprehensive experiments validate that LoRec, as a general framework, significantly strengthens the robustness of sequential recommender systems.
  arXiv  Detail & Related papers  (2024-01-31T10:35:53Z)
• Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models [79.0183835295533]
  We introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to assess the risk of such vulnerabilities.<n>Our analysis identifies two key factors contributing to their success: LLMs' inability to distinguish between informational context and actionable instructions, and their lack of awareness in avoiding the execution of instructions within external content.<n>We propose two novel defense mechanisms-boundary awareness and explicit reminder-to address these vulnerabilities in both black-box and white-box settings.
  arXiv  Detail & Related papers  (2023-12-21T01:08:39Z)
• Hijacking Large Language Models via Adversarial In-Context Learning [10.416972293173993]
  In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts.<n>Existing attacks are either easy to detect, require a trigger in user input, or lack specificity towards ICL.<n>This work introduces a novel transferable prompt injection attack against ICL, aiming to hijack LLMs to generate the target output or elicit harmful responses.
  arXiv  Detail & Related papers  (2023-11-16T15:01:48Z)
• Attack Prompt Generation for Red Teaming and Defending Large Language Models [70.157691818224]
  Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. We propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts.
  arXiv  Detail & Related papers  (2023-10-19T06:15:05Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.