Skip to content
← Back to explorer

Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG

Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy, Chiara Picardi, Amit Giloni, Roman Vainshtein, Andrés Murillo, Hisashi Kojima, Motoyoshi Sekiya, Yuki Unno, Junichi Suga · Feb 24, 2026 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Feb 24, 2026, 11:52 PM

Stale

Extraction refreshed

Apr 13, 2026, 6:44 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.35

Abstract

Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components. We formulate this security challenge as a Partially Observable Markov Decision Process (POMDP), where adversarial intent is a latent variable inferred from noisy multi-stage observations. We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust Agent (MTA) that maintains an approximate belief state via structured LLM reasoning. Operating as a model-agnostic overlay, MMA-RAGT mediates a configurable set of internal checkpoints to enforce stateful defence-in-depth. Extensive evaluation on 43,774 instances demonstrates a 6.50x average reduction factor in Attack Success Rate relative to undefended baselines, with negligible utility cost. Crucially, a factorial ablation validates our theoretical bounds: while statefulness and spatial coverage are individually necessary (26.4 pp and 13.6 pp gains respectively), stateless multi-point intervention can yield zero marginal benefit under homogeneous stateless filtering when checkpoint detections are perfectly correlated.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.35 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.

Reported Metrics

partial

Success rate, Cost, Jailbreak success rate

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Extensive evaluation on 43,774 instances demonstrates a 6.50x average reduction factor in Attack Success Rate relative to undefended baselines, with negligible utility cost.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: General
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.35
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

success ratecostjailbreak success rate

Research Brief

Deterministic synthesis

Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Apr 13, 2026, 6:44 AM · Grounded in abstract + metadata only

Key Takeaways

  • Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation…
  • We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust Agent (MTA) that maintains an approximate belief state via structured LLM reasoning.

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (success rate, cost, jailbreak success rate).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.
  • We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust Agent (MTA) that maintains an approximate belief state via structured LLM reasoning.
  • Extensive evaluation on 43,774 instances demonstrates a 6.50x average reduction factor in Attack Success Rate relative to undefended baselines, with negligible utility cost.

Why It Matters For Eval

  • Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components.
  • We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust Agent (MTA) that maintains an approximate belief state via structured LLM reasoning.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: success rate, cost, jailbreak success rate

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote