Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models

Hieu Xuan Le, Benjamin Goh, Quy Anh Tang

Published

Mar 26, 2026

Citations

0

Trust level

Moderate

Usefulness score

57/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 26, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

General Llm As Judge Red Team

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The abstract does not clearly name benchmarks or metrics.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
57/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while high-capacity LLM-based judges remain too slow or costly for live enforcement. In this work, we examine whether lightweight, general-purpose LLMs can reliably serve as security judges under real-world production constraints. Through careful prompt and output design, lightweight LLMs are guided through a structured reasoning process involving explicit intent decomposition, safety-signal verification, harm assessment, and self-reflection. We evaluate our method on a curated dataset combining benign queries from real-world chatbots with adversarial prompts generated via automated red teaming (ART), covering diverse and evolving patterns. Our results show that general-purpose LLMs, such as gemini-2.0-flash-lite-001, can serve as effective low-latency judges for live guardrails. This configuration is currently deployed in production as a centralized guardrail service for public service chatbots in Singapore. We additionally evaluate a Mixture-of-Models (MoM) setting to assess whether aggregating multiple LLM judges improves prompt-attack detection performance relative to single-model judges, with only modest gains observed.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Red Team

Directly usable for protocol triage.

"Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems."

Evaluation Modes

strong

Llm As Judge

Includes extracted eval setup.

"Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Red Team
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Llm As Judge
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems.
  • In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while high-capacity LLM-based judges remain too slow or costly for live enforcement.
  • In this work, we examine whether lightweight, general-purpose LLMs can reliably serve as security judges under real-world production constraints.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while…
  • In this work, we examine whether lightweight, general-purpose LLMs can reliably serve as security judges under real-world production constraints.
  • We evaluate our method on a curated dataset combining benign queries from real-world chatbots with adversarial prompts generated via automated red teaming (ART), covering diverse and evolving patterns.

Why it matters for eval

  • In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while…
  • In this work, we examine whether lightweight, general-purpose LLMs can reliably serve as security judges under real-world production constraints.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Red Team

  • Evaluation mode is explicit

    Detected: Llm As Judge

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.