Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions

• URL: http://arxiv.org/abs/2607.19061v2
• Date: Wed, 22 Jul 2026 15:00:29 GMT
• Title: Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions
• Abstract summary: We formulate hidden hateful illusion detection as a perceptual retrieval problem.<n> Adaptive View Retrieval assembles a complementary view bank for the image and hidden-message templates.<n>It substantially outperforms original-view baselines and fixed single-transform filters across hate slangs, hate symbols, and visibility levels.
• Score: 0.6138671548064355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hateful optical illusions expose a serious gap in current multimodal safety systems. On original-view hateful illusions, previous work shows that six moderation classifiers achieve at most 20.9 to 24.5% accuracy and nine state-of-the-art VLMs remain at or below 10.2% with illusion-aware prompting, leaving most hidden hate undetected. We formulate hidden hateful illusion detection as a perceptual retrieval problem and propose Adaptive View Retrieval. This retrieve-and-calibrate framework assembles a complementary view bank for the image and hidden-message templates, adaptively selects which views to trust, retrieves hidden-message identities, and calibrates whether the recovered evidence is harmful. On HatefulIllusion with a frozen CLIP encoder, Adaptive View Retrieval reaches 93.2% balanced accuracy on the held-out test split. It substantially outperforms original-view baselines and fixed single-transform filters across hate slangs, hate symbols, and visibility levels. The same design also surpasses official fine-tuned CLIP baselines, matches or exceeds human performance on IllusionMNIST, IllusionFashionMNIST, and IllusionAnimals, and outperforms zoom-out preprocessing on HC-Bench under the SemVink protocol. Together, these results show that robust multimodal moderation requires recovering hidden meaning before deciding whether it is harmful.

Related papers

• Look Clearly Before Answering: Mitigating Hallucinations in LVLMs via Saliency-Driven Perceptual Realignment [45.92240827409312]
  Saliency-Driven Perceptual Realignment (SDPR) is a training-free framework that mitigates the degradation of visual awareness throughout inference.<n>Our proposed SDPR is robust against hallucinations due to its holistic alignment of visual awareness across the entire generative trajectory.
  arXiv  Detail & Related papers  (2026-07-18T14:39:16Z)
• Detecting Clinical Hallucinations in LVLMs via Counterfactual Visual Grounding Uncertainty [22.008964207160663]
  We present a vision-traceable hallucination detection framework that audits arbitrary LVLM responses via visual evidence grounding.<n>We extract visually verifiable entities and use a medical-domain-adapted Qwen-VL grounding verifier to localize each entity on the input image.<n>Experiments on multiple medical imaging modalities and LVLM backbones demonstrate that our method consistently improves hallucination detection performance.
  arXiv  Detail & Related papers  (2026-06-26T18:15:38Z)
• FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition [54.31138496553705]
  Fine-grained recognition in everyday life is often not a closed-book classification problem.<n>Existing benchmarks primarily evaluate visually recognition, leaving this active external knowledge acquisition ability underexplored.<n>We study fine-grained knowledge acquisition, where a system must seek, verify, and use external evidence to answer open-ended fine-grained recognition questions.
  arXiv  Detail & Related papers  (2026-05-13T08:49:51Z)
• Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models [11.342804429826936]
  Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences.<n>This paper presents a training-free framework for the 5th DataCV Challenge Task 1 at CVPR 2026, addressing this perception-versus-memory conflict.<n>Our solution secured 2nd place in the challenge, only 0.47% behind the 1st-place solution.
  arXiv  Detail & Related papers  (2026-05-09T09:52:23Z)
• Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions [26.051334752537546]
  We investigate the risks of scalable hateful illusion generation and the potential for bypassing current content moderation models.<n>We generate 1,860 optical illusions using Stable Diffusion and ControlNet conditioned on 62 hate messages.<n>Of these, 1,571 are hateful illusions that successfully embed hate messages, either overtly or subtly, forming the Hateful Illusion dataset.
  arXiv  Detail & Related papers  (2025-07-30T12:37:29Z)
• Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models [24.363156120809546]
  We propose KIE-HVQA, the first benchmark dedicated to evaluating OCR hallucination in degraded document understanding.<n>This dataset includes test samples spanning identity cards and invoices, with simulated real-world degradations for OCR reliability.<n>Experiments on Qwen2.5-VL demonstrate that our 7B- parameter model achieves a 22% absolute improvement in hallucination-free accuracy over GPT-4o.
  arXiv  Detail & Related papers  (2025-06-25T06:44:07Z)
• ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs [98.27348724529257]
  We introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of human-written image captions.<n>Models trained with the ViCrit Task exhibit substantial gains across a variety of vision-language models benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T19:16:54Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [78.78822033285938]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations.<n>In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification.
  arXiv  Detail & Related papers  (2025-04-17T17:59:22Z)
• IllusionBench+: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models [56.34742191010987]
  Current Visual Language Models (VLMs) show impressive image understanding but struggle with visual illusions.<n>We introduce IllusionBench, a comprehensive visual illusion dataset that encompasses classic cognitive illusions and real-world scene illusions.<n>We design trap illusions that resemble classical patterns but differ in reality, highlighting issues in SOTA models.
  arXiv  Detail & Related papers  (2025-01-01T14:10:25Z)
• Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning [54.15303628138665]
  Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance. We propose Dual Spoof Disentanglement Generation framework to tackle this challenge by "anti-spoofing via generation"
  arXiv  Detail & Related papers  (2021-12-01T15:36:59Z)
• Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting System [103.5604680001633]
  Anti-spoofing against high-resolution rendering replay of paper photos or digital videos remains an open problem. We propose a simple yet effective face anti-spoofing system, termed Aurora Guard (AG)
  arXiv  Detail & Related papers  (2021-02-01T09:17:18Z)

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.