Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings

• URL: http://arxiv.org/abs/2608.17556v1
• Date: Tue, 18 Aug 2026 09:19:22 GMT
• Title: Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings
• Abstract summary: This paper introduces Reflex-Guard, a lightweight guardrail that runs locally.<n>It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers.<n>It achieves 95.9% recall on harmful prompts at 37.6 ms end-to-end latency.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms. Furthermore, routing user prompts through external moderation endpoints raises significant data privacy concerns. This paper introduces Reflex-Guard, a lightweight guardrail that runs locally. It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers. Together, these components enable high-accuracy prompt safety filtering with much lower latency than existing solutions. Through systematic evaluation on a strategically balanced dataset of 30,568 samples drawn from five complementary sources, we demonstrate that Reflex-Guard achieves 95.9% recall on harmful prompts at 37.6 ms end-to-end latency. It is faster than existing baselines, including Llama Guard 2 at 255 ms and SafeDecoding at 723 ms. It can detect 100% of GCG suffix attacks and Base64-encoded prompts using the default threshold. However, DrAttack structured prompts required lowering the threshold to 0.03 for optimal detection, as they produced a distinct probability distribution. Reflex-Guard achieves Reflex Efficiency Score (RES) scores up to 16.79, significantly outperforming Llama Guard 2 (11.90) and SafeDecoding (9.80). This analysis offers practical deployment advice and shows that different attack types occupy distinct regions in the embedding probability space.

Related papers

• Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection [5.902327401962825]
  We present Reflect-Guard, a method that augments LLM-based safety classifiers with chain-of-thought self-reflection capabilities.<n>Our approach distills analytical reasoning from GPT-4o-mini into structured annotations, then trains Llama-Guard-3-8B via QLoRA to generate logical self-reflections.<n>Using only 1000 training examples and updating just 0.5% of model parameters, Reflect-Guard achieves substantial improvements on two challenging benchmarks.
  arXiv  Detail & Related papers  (2026-05-24T02:58:21Z)
• AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use [2.9991161518367875]
  AgentTrust intercepts agent tool calls before execution and returns a structured verdict: allow, warn, block, or review.<n>We release a 300-scenario benchmark across six risk categories and an additional 630 independently constructed real-world adversarial scenarios.<n>On the 630-second benchmark, evaluated under a patched ruleset, AgentTrust achieves 96.7% verdict accuracy, including about 93% on shell-obfuscated payloads.
  arXiv  Detail & Related papers  (2026-05-06T11:38:16Z)
• Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs [51.56484100374058]
  guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency.<n>We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural validation, contextual sandboxing, and session-level behavioral checks.<n>Results expose operational trade-offs: NeMo reaches 0 percent bypass at 16.22 percent FPR and roughly 1.5s latency, while Prompt Guard yields 38.48 percent bypass with 3.60 percent FPR.
  arXiv  Detail & Related papers  (2026-03-29T18:52:01Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• 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)
• AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software [11.606665113249298]
  Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software.<n>We propose AdaptiveGuard, an adaptive guardrail that detects novel jailbreak attacks as out-of-distribution (OOD) inputs.<n>We show that AdaptiveGuard achieves 96% OOD detection accuracy, adapts to new attacks in just two update steps, and retains over 85% F1-score on in-distribution data post-adaptation.
  arXiv  Detail & Related papers  (2025-09-21T01:22:42Z)
• LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities [1.460362586787935]
  LiteLMGuard (LLMG) provides real-time, prompt-level defense for quantized SLMs.<n>LLMG formalizes prompt filtering as a deep learning (DL)-based prompt answerability classification task.<n>LLMG defends against over 87% of harmful prompts, including both direct instruction and jailbreak attack strategies.
  arXiv  Detail & Related papers  (2025-05-08T19:58:41Z)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)
• WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs [54.10865585773691]
  We introduce WildGuard -- an open, light-weight moderation tool for LLM safety.<n>WildGuard achieves three goals: identifying malicious intent in user prompts, detecting safety risks of model responses, and determining model refusal rate.
  arXiv  Detail & Related papers  (2024-06-26T16:58:20Z)
• OR-Bench: An Over-Refusal Benchmark for Large Language Models [65.34666117785179]
  Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs.<n>This study proposes a novel method for automatically generating large-scale over-refusal datasets.<n>We introduce OR-Bench, the first large-scale over-refusal benchmark.
  arXiv  Detail & Related papers  (2024-05-31T15:44:33Z)

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.