mlsanityData to 7 Oct 2026

MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

arXiv 2406.07057 ↗First posted 11 Jun 2024cs.CL cs.AI cs.CVcited by 51

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holistic evaluation to offer thorough insights into future improvements. In this work, we establish MultiTrust, the first comprehensive and unified benchmark on the trustworthiness of MLLMs across five primary aspects: truthfulness, safety, robustness, fairness, and privacy. Our benchmark employs a rigorous evaluation strategy that addresses both multimodal risks and cross-modal impacts, encompassing 32 diverse tasks with self-curated datasets. Extensive experiments with 21 modern MLLMs reveal some previously unexplored trustworthiness issues and risks, highlighting the complexities introduced by the multimodality and underscoring the necessity for advanced methodologies to enhance their reliability. For instance, typical proprietary models still struggle with the perception of visually confusing images and are vulnerable to multimodal jailbreaking and adversarial attacks; MLLMs are more inclined to disclose privacy in text and reveal ideological and cultural biases even when paired with irrelevant images in inference, indicating that the multimodality amplifies the internal risks from base LLMs. Additionally, we release a scalable toolbox for standardized trustworthiness research, aiming to facilitate future advancements in this important field. Code and resources are publicly available at: https://multi-trust.github.io/.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 84 of its 185 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

84 of 185 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks3 Apr
  2. 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast13 Feb
  3. 2024Red Teaming Visual Language Models23 Jan
  4. 2023MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models29 Nov
  5. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts9 Nov
  6. 2023Can Language Models be Instructed to Protect Personal Information?3 Oct

Other references · 78

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2023Mistral 7Bcited by 3,065
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  7. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  8. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  9. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  11. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  12. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
38 more
  1. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  2. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  3. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  4. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  5. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  6. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  7. 2023PaLM 2 Technical Reportcited by 1,154
  8. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  9. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,000
  10. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 929
  11. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 893
  12. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  13. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  14. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  15. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  16. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  17. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 572
  18. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 548
  19. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 545
  20. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Promptscited by 520
  21. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 478
  22. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 457
  23. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  24. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  25. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  26. 2024Hallucination of Multimodal Large Language Models: A Surveycited by 380
  27. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
  28. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  29. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
  30. 2024A Survey on Hallucination in Large Vision-Language Modelscited by 352
  31. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  32. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  33. 2024TrustLLM: Trustworthiness in Large Language Modelscited by 280
  34. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 266
  35. 2023AI Alignment: A Comprehensive Surveycited by 256
  36. 2023Large Language Model Alignment: A Surveycited by 241
  37. 2024MM1: Methods, Analysis & Insights from Multimodal LLM Pre-trainingcited by 230
  38. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Promptscited by 218

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 33; 2026: 9.

51 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  2. 2024A Survey on Benchmarks of Multimodal Large Language Modelscited by 81
  3. 2024MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMscited by 72
  4. 2025STAIR: Improving Safety Alignment with Introspective Reasoningcited by 72
  5. 2024T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Modelscited by 66
  6. 2025A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluationscited by 66
  7. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  8. 2024A Survey on Evaluation of Multimodal Large Language Modelscited by 46
  9. 2025EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Modelscited by 32
  10. 2025A Survey on Autonomy-Induced Security Risks in Large Model-Based Agentscited by 28
  11. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  12. 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMscited by 25
38 more
  1. 2025MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environmentscited by 23
  2. 2025Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMscited by 20
  3. 2024Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarioscited by 19
  4. 2025HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluationcited by 19
  5. 2025RvLLM: LLM Runtime Verification with Domain Knowledgecited by 15
  6. 2025DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarioscited by 14
  7. 2025Aligning Multimodal LLM with Human Preference: A Surveycited by 12
  8. 2025Privacy Reasoning in Ambiguous Contextscited by 11
  9. 2025Towards Safe Reasoning in Large Reasoning Models via Corrective Interventioncited by 11
  10. 2025VLDBench Evaluating Multimodal Disinformation with Regulatory Alignmentcited by 8
  11. 2025Red-Teaming Text-to-Image Systems by Rule-based Preference Modelingcited by 8
  12. 2025Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Modelscited by 8
  13. 2024Can visual language models resolve textual ambiguity with visual cues? Let visual puns tell you!cited by 7
  14. 2024AI Benchmarks and Datasets for LLM Evaluationcited by 7
  15. 2025Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Modelscited by 7
  16. 2025CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcarecited by 7
  17. 2025Multimodal Safety Evaluation in Generative Agent Social Simulationscited by 5
  18. 2025Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigationcited by 4
  19. 2025Bias in the Picture: Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessmentcited by 3
  20. 2026PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attentioncited by 3
  21. 2026SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognitioncited by 3
  22. 2025FairReason: Balancing Reasoning and Social Bias in MLLMscited by 2
  23. 2025OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Modelscited by 2
  24. 2025Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilitiescited by 2
  25. 2025VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attackcited by 2
  26. 2025Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attackscited by 2
  27. 2026Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimizationcited by 2
  28. 2025ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstractioncited by 1
  29. 2025LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Modelscited by 1
  30. 2025On the Robustness of Vision-Language Models in Zero-shot Privacy Classificationcited by 1
  31. 2025NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generationcited by 1
  32. 2026Confidence-Aware Tool Orchestration for Robust Video Understandingcited by 1
  33. 2025When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoningcited by 0
  34. 2025Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoningcited by 0
  35. 2026AviationLMM: A Large Multimodal Foundation Model for Civil Aviationcited by 0
  36. 2026EVA: Editing for Versatile Alignment against Jailbreakscited by 0
  37. 2026Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMscited by 0
  38. 2026VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agentscited by 0

50 most cited of 51 All 51 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
  2. 2024Multimodal Large Language Models to Support Real-World Fact-Checking
  3. 2025MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions
  4. 2026Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
  5. 2024Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
  6. 2026Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
  7. 2024Safety of Multimodal Large Language Models on Images and Texts
  8. 2025Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models