Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities

• URL: http://arxiv.org/abs/2507.11155v1
• Date: Tue, 15 Jul 2025 10:04:27 GMT
• Title: Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
• Authors: Yiting Qu, Michael Backes, Yang Zhang,
• Abstract summary: Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images.<n>It is still unclear whether they can recognize various unsafe concepts when presented in different modalities, such as text and images.<n>We conduct a systematic evaluation of VLMs' perception (concept recognition) and alignment (ethical reasoning) capabilities.<n>We introduce a simplified reinforcement learning (RL)-based approach using proximal policy optimization (PPO) to strengthen the ability to identify unsafe concepts from images.
• Score: 23.165174248333212
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various unsafe concepts when presented in different modalities, such as text and images. To address this, we first compile the UnsafeConcepts dataset, featuring 75 unsafe concepts, i.e., ``Swastika,'' ``Sexual Harassment,'' and ``Assaults,'' along with associated 1.5K images. We then conduct a systematic evaluation of VLMs' perception (concept recognition) and alignment (ethical reasoning) capabilities. We assess eight popular VLMs and find that, although most VLMs accurately perceive unsafe concepts, they sometimes mistakenly classify these concepts as safe. We also identify a consistent modality gap among open-source VLMs in distinguishing between visual and textual unsafe concepts. To bridge this gap, we introduce a simplified reinforcement learning (RL)-based approach using proximal policy optimization (PPO) to strengthen the ability to identify unsafe concepts from images. Our approach uses reward scores based directly on VLM responses, bypassing the need for collecting human-annotated preference data to train a new reward model. Experimental results show that our approach effectively enhances VLM alignment on images while preserving general capabilities. It outperforms baselines such as supervised fine-tuning (SFT) and direct preference optimization (DPO). We hope our dataset, evaluation findings, and proposed alignment solution contribute to the community's efforts in advancing safe VLMs.

Related papers

• HoliSafe: Holistic Safety Benchmarking and Modeling with Safety Meta Token for Vision-Language Model [52.72318433518926]
  Existing safety-tuning datasets and benchmarks only partially consider how image-text interactions can yield harmful content.<n>We introduce a holistic safety dataset and benchmark, HoliSafe, that spans all five safe/unsafe image-text combinations.<n>We propose SafeLLaVA, a novel VLM augmented with a learnable safety meta token and a dedicated safety head.
  arXiv  Detail & Related papers  (2025-06-05T07:26:34Z)
• Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment? [73.80382983108997]
  Representation intervention aims to locate and modify the representations that encode the underlying concepts in Large Language Models.<n>If the interventions are faithful, the intervened LLMs should erase the harmful concepts and be robust to both in-distribution adversarial prompts and the out-of-distribution jailbreaks.<n>We propose Concept Concentration (COCA), which simplifies the decision boundary between harmful and benign representations.
  arXiv  Detail & Related papers  (2025-05-24T12:23:52Z)
• REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models [59.445672459851274]
  REVAL is a comprehensive benchmark designed to evaluate the textbfREliability and textbfVALue of Large Vision-Language Models.<n>REVAL encompasses over 144K image-text Visual Question Answering (VQA) samples, structured into two primary sections: Reliability and Values.<n>We evaluate 26 models, including mainstream open-source LVLMs and prominent closed-source models like GPT-4o and Gemini-1.5-Pro.
  arXiv  Detail & Related papers  (2025-03-20T07:54:35Z)
• Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidance [41.6755826072905]
  In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories.<n>Existing vision-language models often underperform in real-world applications because of sub-optimal prompt engineering.<n>We propose a Concept-guided Human-like Bayesian Reasoning framework to address these issues.
  arXiv  Detail & Related papers  (2025-03-20T06:20:13Z)
• Hyperbolic Safety-Aware Vision-Language Models [44.06996781749013]
  We introduce a novel approach that shifts from unlearning to an awareness paradigm by leveraging the inherent hierarchical properties of the hyperbolic space.<n>Our HySAC, Hyperbolic Safety-Aware CLIP, employs entailment loss functions to model the hierarchical and asymmetrical relations between safe and unsafe image-text pairs.<n>Our approach not only enhances safety recognition but also establishes a more adaptable and interpretable framework for content moderation in vision-language models.
  arXiv  Detail & Related papers  (2025-03-15T13:18:04Z)
• Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs [56.440345471966666]
  Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images.<n>This paper introduces MMSafeAware, the first comprehensive multimodal safety awareness benchmark designed to evaluate MLLMs across 29 safety scenarios.<n> MMSafeAware includes both unsafe and over-safety subsets to assess models abilities to correctly identify unsafe content and avoid over-sensitivity that can hinder helpfulness.
  arXiv  Detail & Related papers  (2025-02-16T16:12:40Z)
• MLLM-as-a-Judge for Image Safety without Human Labeling [81.24707039432292]
  In the age of AI-generated content (AIGC), many image generation models are capable of producing harmful content.<n>It is crucial to identify such unsafe images based on established safety rules.<n>Existing approaches typically fine-tune MLLMs with human-labeled datasets.
  arXiv  Detail & Related papers  (2024-12-31T00:06:04Z)
• Retention Score: Quantifying Jailbreak Risks for Vision Language Models [60.48306899271866]
  Vision-Language Models (VLMs) are integrated with Large Language Models (LLMs) to enhance multi-modal machine learning capabilities.<n>This paper aims to assess the resilience of VLMs against jailbreak attacks that can compromise model safety compliance and result in harmful outputs.<n>To evaluate a VLM's ability to maintain its robustness against adversarial input perturbations, we propose a novel metric called the textbfRetention Score.
  arXiv  Detail & Related papers  (2024-12-23T13:05:51Z)
• PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment [28.008884416277954]
  We propose a progressive concept-based alignment strategy, PSA-VLM, to enhance visual modality safety alignment.<n>Our method achieves state-of-the-art results on popular VLM safety benchmark.
  arXiv  Detail & Related papers  (2024-11-18T13:01:57Z)
• ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time [12.160713548659457]
  adversarial visual inputs can easily bypass VLM defense mechanisms.<n>We propose a novel two-phase inference-time alignment framework, evaluating input visual contents and output responses.<n>Experiments show that ETA outperforms baseline methods in terms of harmlessness, helpfulness, and efficiency.
  arXiv  Detail & Related papers  (2024-10-09T07:21:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.