Skip to content
← Back to explorer

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding

Junxian Li, Beining Xu, Simin Chen, Jiatong Li, Jingdi Lei, Haodong Zhao, Di Zhang · Aug 13, 2025 · 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

Mar 7, 2026, 7:35 PM

Recent

Extraction refreshed

Mar 14, 2026, 3:12 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.35

Abstract

Recent advances in vision-language models (VLMs) have significantly enhanced the visual grounding task, which involves locating objects in an image based on natural language queries. Despite these advancements, the security of VLM-based grounding systems has not been thoroughly investigated. This paper reveals a novel and realistic vulnerability: the first multi-target backdoor attack on VLM-based visual grounding. Unlike prior attacks that rely on static triggers or fixed targets, we propose IAG, a method that dynamically generates input-aware, text-guided triggers conditioned on any specified target object description to execute the attack. This is achieved through a text-conditioned UNet that embeds imperceptible target semantic cues into visual inputs while preserving normal grounding performance on benign samples. We further develop a joint training objective that balances language capability with perceptual reconstruction to ensure imperceptibility, effectiveness, and stealth. Extensive experiments on multiple VLMs (e.g., LLaVA, InternVL, Ferret) and benchmarks (RefCOCO, RefCOCO+, RefCOCOg, Flickr30k Entities, and ShowUI) demonstrate that IAG achieves the best ASRs compared with other baselines on almost all settings without compromising clean accuracy, maintaining robustness against existing defenses, and exhibiting transferability across datasets and models. These findings underscore critical security risks in grounding-capable VLMs and highlight the need for further research on trustworthy multimodal understanding.

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: Recent advances in vision-language models (VLMs) have significantly enhanced the visual grounding task, which involves locating objects in an image based on natural language queries.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Recent advances in vision-language models (VLMs) have significantly enhanced the visual grounding task, which involves locating objects in an image based on natural language queries.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Recent advances in vision-language models (VLMs) have significantly enhanced the visual grounding task, which involves locating objects in an image based on natural language queries.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Recent advances in vision-language models (VLMs) have significantly enhanced the visual grounding task, which involves locating objects in an image based on natural language queries.

Reported Metrics

partial

Accuracy

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Extensive experiments on multiple VLMs (e.g., LLaVA, InternVL, Ferret) and benchmarks (RefCOCO, RefCOCO+, RefCOCOg, Flickr30k Entities, and ShowUI) demonstrate that IAG achieves the best ASRs compared with other baselines on almost all settings without compromising clean accuracy, maintaining robustness against existing defenses, and exhibiting transferability across datasets and models.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Recent advances in vision-language models (VLMs) have significantly enhanced the visual grounding task, which involves locating objects in an image based on natural language queries.

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

accuracy

Research Brief

Deterministic synthesis

Unlike prior attacks that rely on static triggers or fixed targets, we propose IAG, a method that dynamically generates input-aware, text-guided triggers conditioned on any specified target object description to execute the attack. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 14, 2026, 3:12 AM · Grounded in abstract + metadata only

Key Takeaways

  • Unlike prior attacks that rely on static triggers or fixed targets, we propose IAG, a method that dynamically generates input-aware, text-guided triggers conditioned on any…
  • Extensive experiments on multiple VLMs (e.g., LLaVA, InternVL, Ferret) and benchmarks (RefCOCO, RefCOCO+, RefCOCOg, Flickr30k Entities, and ShowUI) demonstrate that IAG achieves…

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 (accuracy).

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

  • Unlike prior attacks that rely on static triggers or fixed targets, we propose IAG, a method that dynamically generates input-aware, text-guided triggers conditioned on any specified target object description to execute the attack.
  • Extensive experiments on multiple VLMs (e.g., LLaVA, InternVL, Ferret) and benchmarks (RefCOCO, RefCOCO+, RefCOCOg, Flickr30k Entities, and ShowUI) demonstrate that IAG achieves the best ASRs compared with other baselines on almost all…

Why It Matters For Eval

  • Extensive experiments on multiple VLMs (e.g., LLaVA, InternVL, Ferret) and benchmarks (RefCOCO, RefCOCO+, RefCOCOg, Flickr30k Entities, and ShowUI) demonstrate that IAG achieves the best ASRs compared with other baselines on almost all…

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: accuracy

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