Skip to content
← Back to explorer

LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops

Jiyuan Fu, Kaixun Jiang, Lingyi Hong, Jinglun Li, Haijing Guo, Dingkang Yang, Zhaoyu Chen, Wenqiang Zhang · Jun 17, 2025 · Citations: 0

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

Mar 30, 2026, 8:41 AM

Recent

Extraction refreshed

Apr 12, 2026, 6:51 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.20

Abstract

Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference. Attackers can exploit this by inducing excessive output, leading to resource exhaustion and service degradation. Prior energy-latency attacks aim to increase generation time by broadly shifting the output token distribution away from the EOS token, but they neglect the influence of token-level Part-of-Speech (POS) characteristics on EOS and sentence-level structural patterns on output counts, limiting their efficacy. To address this, we propose LingoLoop, an attack designed to induce MLLMs to generate excessively verbose and repetitive sequences. First, we find that the POS tag of a token strongly affects the likelihood of generating an EOS token. Based on this insight, we propose a POS-Aware Delay Mechanism to postpone EOS token generation by adjusting attention weights guided by POS information. Second, we identify that constraining output diversity to induce repetitive loops is effective for sustained generation. We introduce a Generative Path Pruning Mechanism that limits the magnitude of hidden states, encouraging the model to produce persistent loops. Extensive experiments on models like Qwen2.5-VL-3B demonstrate LingoLoop's powerful ability to trap them in generative loops; it consistently drives them to their generation limits and, when those limits are relaxed, can induce outputs with up to 367x more tokens than clean inputs, triggering a commensurate surge in energy consumption. These findings expose significant MLLMs' vulnerabilities, posing challenges for their reliable deployment.

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 0.20 (below strong-reference threshold).
  • No explicit evaluation mode was extracted from available metadata.
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

Background context only.

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

Weak / implicit signal

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: Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference.

Evaluation Modes

missing

None explicit

Confidence: Low Source: Persisted extraction missing

Validate eval design from full paper text.

Evidence snippet: Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference.

Reported Metrics

partial

Latency

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Prior energy-latency attacks aim to increase generation time by broadly shifting the output token distribution away from the EOS token, but they neglect the influence of token-level Part-of-Speech (POS) characteristics on EOS and sentence-level structural patterns on output counts, limiting their efficacy.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Multimodal Large Language Models (MLLMs) have shown great promise but require substantial computational resources during inference.

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:
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.20
  • 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

latency

Research Brief

Deterministic synthesis

To address this, we propose LingoLoop, an attack designed to induce MLLMs to generate excessively verbose and repetitive sequences. HFEPX protocol signal is limited in abstract-level metadata, so treat it as adjacent context. Updated from current HFEPX corpus.

Generated Apr 12, 2026, 6:51 AM · Grounded in abstract + metadata only

Key Takeaways

  • To address this, we propose LingoLoop, an attack designed to induce MLLMs to generate excessively verbose and repetitive sequences.
  • Based on this insight, we propose a POS-Aware Delay Mechanism to postpone EOS token generation by adjusting attention weights guided by POS information.
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

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 (latency).

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

  • To address this, we propose LingoLoop, an attack designed to induce MLLMs to generate excessively verbose and repetitive sequences.
  • Based on this insight, we propose a POS-Aware Delay Mechanism to postpone EOS token generation by adjusting attention weights guided by POS information.
  • We introduce a Generative Path Pruning Mechanism that limits the magnitude of hidden states, encouraging the model to produce persistent loops.

Why It Matters For Eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • 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: latency

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