Prompt Overflow: What the Guardrail Inspects Is Not What the Model Infers

• URL: http://arxiv.org/abs/2605.23196v1
• Date: Fri, 22 May 2026 03:27:18 GMT
• Title: Prompt Overflow: What the Guardrail Inspects Is Not What the Model Infers
• Abstract summary: Guardrail models are widely deployed to screen user inputs before they reach large language models (LLMs)<n>We introduce a novel Prompt Overflow Attack, which exploits a mismatch between the limited inspection windows of guardrail models and the substantially larger context inference windows of downstream LLMs.<n>We demonstrate that prompts reliably detected in short-context settings can evade guardrail models once adversarially manipulated into over-length inputs.
• Score: 22.77036856603702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these models handle overlength prompts through truncation or segmentation-based inspection. While prior work has focused on semantic adversarial inputs, the security implications of these long-input processing mechanisms remain largely unexplored. In this paper, we identify a critical blind spot arising from the mismatch between the limited inspection windows of guardrail models and the substantially larger context inference windows of downstream LLMs. We introduce a novel Prompt Overflow Attack, which exploits this mismatch by fragmenting malicious instructions and interleaving them with benign filler content across an overlong prompt, such that no individual inspected segment appears malicious while the full context remains actionable to the LLM. Through a systematic evaluation against state-of-the-art guardrail models, including Meta Llama Prompt Guard, IBM Granite Guardian, and DeBERTa-based detectors, we demonstrate that prompts reliably detected in short-context settings can evade guardrail models once adversarially manipulated into over-length inputs, yet remain fully actionable by downstream LLMs. We further propose potential defense strategies and outline mitigation directions to strengthen guardrail models.

Related papers

• Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces [32.850551109913845]
  Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs)<n>We show that this prompt-centric paradigm overlooks a structural vulnerability in stateful, function-calling environments.<n>We exploit this architectural flaw through SMT, a black-box attack framework based on Simulated Moderation Traces.
  arXiv  Detail & Related papers  (2026-07-01T06:08:07Z)
• One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue [55.98008208209856]
  Hidden malicious intent in multi-turn dialogue poses a growing threat to large language models (LLMs)<n>Recent studies show that even modern commercial models with advanced guardrails remain vulnerable to such attacks despite advances in safety alignment and external guardrails.<n>In this work, we address this challenge by detecting the earliest turn at which delivering the candidate response would make the accumulated interaction sufficient to enable harmful action.
  arXiv  Detail & Related papers  (2026-05-07T03:35:31Z)
• Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models [0.0]
  Prompt attacks pose a critical security risk to Large Language Model systems.<n>In production, guardrails must mitigate these attacks under strict low-latency constraints.<n>We show that general-purpose LLMs can serve as effective low-latency judges for live guardrails.
  arXiv  Detail & Related papers  (2026-03-26T08:47:53Z)
• Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement [13.976796671311066]
  Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent.<n>We introduce a self-supervised framework for disentangling semantic factor pairs in LLM activations at inference.<n>We then propose FrameShield, an anomaly detector operating on the framing representations, which improves model-agnostic detection.
  arXiv  Detail & Related papers  (2026-02-23T00:11:30Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Black-Box Guardrail Reverse-engineering Attack [12.937652779951156]
  We present the first study of black-box LLM guardrail reverse-engineering attacks.<n>We propose Guardrail Reverse-engineering Attack (GRA), a reinforcement learning-based framework.<n>GRA achieves a rule matching rate exceeding 0.92 while requiring less than $85 in API costs.
  arXiv  Detail & Related papers  (2025-11-06T09:24:49Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security [63.41350337821108]
  We propose Secure Tug-of-War (SecTOW) to enhance the security of multimodal large language models (MLLMs)<n>SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO)<n>We show that SecTOW significantly improves security while preserving general performance.
  arXiv  Detail & Related papers  (2025-07-29T17:39:48Z)
• Robust Anti-Backdoor Instruction Tuning in LVLMs [53.766434746801366]
  We introduce a lightweight, certified-agnostic defense framework for large visual language models (LVLMs)<n>Our framework finetunes only adapter modules and text embedding layers under instruction tuning.<n>Experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero.
  arXiv  Detail & Related papers  (2025-06-04T01:23:35Z)
• 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)

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.