Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling

• URL: http://arxiv.org/abs/2509.07617v1
• Date: Tue, 09 Sep 2025 11:42:06 GMT
• Title: Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
• Authors: Minghui Li, Hao Zhang, Yechao Zhang, Wei Wan, Shengshan Hu, pei Xiaobing, Jing Wang,
• Abstract summary: Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage.<n>To address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box methods, we propose an activations-guided prompt injection attack framework.
• Score: 30.157082498075315
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box methods, we propose an activations-guided prompt injection attack framework. We first construct an Energy-based Model (EBM) using activations from a surrogate model to evaluate the quality of adversarial prompts. Guided by the trained EBM, we employ the token-level Markov Chain Monte Carlo (MCMC) sampling to adaptively optimize adversarial prompts, thereby enabling gradient-free black-box attacks. Experimental results demonstrate our superior cross-model transferability, achieving 49.6% attack success rate (ASR) across five mainstream LLMs and 34.6% improvement over human-crafted prompts, and maintaining 36.6% ASR on unseen task scenarios. Interpretability analysis reveals a correlation between activations and attack effectiveness, highlighting the critical role of semantic patterns in transferable vulnerability exploitation.

Related papers

• Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs [2.2448294058653455]
  adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards.<n>We propose Zero-Shot Embedding Drift Detection (ZEDD), a lightweight, low-engineering-overhead framework that identifies both direct and indirect prompt injection attempts.<n>ZEDD operates without requiring access to model internals, prior knowledge of attack types, or task-specific retraining.
  arXiv  Detail & Related papers  (2026-01-18T11:33:35Z)
• Adversarial Contrastive Learning for LLM Quantization Attacks [28.158356717114845]
  Adversarial Contrastive Learning (ACL) is a gradient-based quantization attack that achieves superior attack effectiveness.<n>ACL formulates the attack objective as a triplet-based contrastive loss, and integrates it with a projected descent two-stage distributed fine-tuning strategy.<n>Experiments demonstrate ACL's remarkable effectiveness, achieving attack success rates of 86.00% for over-refusal, 97.69% for jailbreak, and 92.40% for advertisement injection.
  arXiv  Detail & Related papers  (2026-01-06T03:26:11Z)
• TopicAttack: An Indirect Prompt Injection Attack via Topic Transition [71.81906608221038]
  Large language models (LLMs) are vulnerable to indirect prompt injection attacks.<n>We propose TopicAttack, which prompts the LLM to generate a fabricated transition prompt that gradually shifts the topic toward the injected instruction.<n>We find that a higher injected-to-original attention ratio leads to a greater success probability, and our method achieves a much higher ratio than the baseline methods.
  arXiv  Detail & Related papers  (2025-07-18T06:23:31Z)
• MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks [85.3303135160762]
  MIRAGE is a novel framework that exploits narrative-driven context and role immersion to circumvent safety mechanisms in Multimodal Large Language Models.<n>It achieves state-of-the-art performance, improving attack success rates by up to 17.5% over the best baselines.<n>We demonstrate that role immersion and structured semantic reconstruction can activate inherent model biases, facilitating the model's spontaneous violation of ethical safeguards.
  arXiv  Detail & Related papers  (2025-03-24T20:38:42Z)
• Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving [65.61999354218628]
  We take the first step toward designing black-box adversarial attacks specifically targeting vision-language models (VLMs) in autonomous driving systems.<n>We propose Cascading Adversarial Disruption (CAD), which targets low-level reasoning breakdown by generating and injecting semantics.<n>We present Risky Scene Induction, which addresses dynamic adaptation by leveraging a surrogate VLM to understand and construct high-level risky scenarios.
  arXiv  Detail & Related papers  (2025-01-23T11:10:02Z)
• Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks [34.40254709148148]
  Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding. Their potential safety and robustness issues raise concerns that adversaries may evade the system and cause these models to generate toxic content through malicious attacks. We present Chain of Attack (CoA), which iteratively enhances the generation of adversarial examples based on the multi-modal semantic update.
  arXiv  Detail & Related papers  (2024-11-24T05:28:07Z)
• Defending Large Language Models Against Attacks With Residual Stream Activation Analysis [0.0]
  Large Language Models (LLMs) are vulnerable to adversarial threats.<n>This paper presents an innovative defensive strategy, given white box access to an LLM.<n>We apply a novel methodology for analyzing distinctive activation patterns in the residual streams for attack prompt classification.
  arXiv  Detail & Related papers  (2024-06-05T13:06:33Z)
• Learning diverse attacks on large language models for robust red-teaming and safety tuning [126.32539952157083]
  Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe deployment of large language models.<n>We show that even with explicit regularization to favor novelty and diversity, existing approaches suffer from mode collapse or fail to generate effective attacks.<n>We propose to use GFlowNet fine-tuning, followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts.
  arXiv  Detail & Related papers  (2024-05-28T19:16:17Z)
• 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)
• Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks [56.96241557830253]
  Transfer-based adversarial attacks can effectively evaluate model robustness in the black-box setting. We propose a conditional generative attacking model, which can generate the adversarial examples targeted at different classes. Our method improves the success rates of targeted black-box attacks by a significant margin over the existing methods.
  arXiv  Detail & Related papers  (2021-07-05T06:17:47Z)
• Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution [83.02632136860976]
  We study black-box adversarial attacks against deep neural networks (DNNs) We develop a novel mechanism of adversarial transferability, which is robust to the surrogate biases. Experiments on benchmark datasets and attacking against real-world API demonstrate the superior attack performance of the proposed method.
  arXiv  Detail & Related papers  (2020-06-15T16:45:27Z)

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.