Towards Context-Aware Image Anonymization with Multi-Agent Reasoning

• URL: http://arxiv.org/abs/2603.27817v2
• Date: Fri, 03 Apr 2026 19:55:07 GMT
• Title: Towards Context-Aware Image Anonymization with Multi-Agent Reasoning
• Abstract summary: We present an agentic framework CAIAMAR for context-aware PII segmentation with diffusion-based anonymization.<n>Three specialized agents coordinate via round-robin speaker selection in a Plan-Do-Check-Act cycle.<n>For image quality preservation on CityScapes, we achieve KID: $0.001$, and FID: $9.1$, significantly outperforming existing anonymization.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Street-level imagery contains personally identifiable information (PII), some of which is context-dependent. Existing anonymization methods either over-process images or miss subtle identifiers, while API-based solutions compromise data sovereignty. We present an agentic framework CAIAMAR (\underline{C}ontext-\underline{A}ware \underline{I}mage \underline{A}nonymization with \underline{M}ulti-\underline{A}gent \underline{R}easoning) for context-aware PII segmentation with diffusion-based anonymization, combining pre-defined processing for high-confidence cases with multi-agent reasoning for indirect identifiers. Three specialized agents coordinate via round-robin speaker selection in a Plan-Do-Check-Act (PDCA) cycle, enabling large vision-language models to classify PII based on spatial context (private vs. public property) rather than rigid category rules. The agents implement spatially-filtered coarse-to-fine detection where a scout-and-zoom strategy identifies candidates, open-vocabulary segmentation processes localized crops, and $IoU$-based deduplication ($30\%$ threshold) prevents redundant processing. Modal-specific diffusion guidance with appearance decorrelation substantially reduces re-identification (Re-ID) risks. On CUHK03-NP, our method reduces person Re-ID risk by $73\%$ ($R1$: $16.9\%$ vs. $62.4\%$ baseline). For image quality preservation on CityScapes, we achieve KID: $0.001$, and FID: $9.1$, significantly outperforming existing anonymization. The agentic workflow detects non-direct PII instances across object categories, and downstream semantic segmentation is preserved. Operating entirely on-premise with open-source models, the framework generates human-interpretable audit trails supporting EU's GDPR transparency requirements while flagging failed cases for human review.

Related papers

• Automatic Red Teaming for Implicit Vulnerabilities of Text-to-Image Models [58.59008920408855]
  We propose Adversarial Probing for Implicit VulnErabilities (AdvPIE) to expose implicit vulnerabilities without requiring access to the parameters of target models.<n> AdvPIE adopts a policy agent to generate and refine implicit adversarial prompts based on the feedback from a judge agent.<n>Experiments on standard and safety-aligned T2I models show that AdvPIE1 effectively uncovers implicit vulnerabilities.
  arXiv  Detail & Related papers  (2026-09-05T13:45:09Z)
• FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking [0.0]
  Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns.<n> advanced Generative AI models can now inject localized, high-fidelity manipulations, creating deceptive attacks.<n>FakeIDet3-DB is the first comprehensive database of digital manipulations on real, government-issued IDs.
  arXiv  Detail & Related papers  (2026-07-29T09:03:29Z)
• Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity [36.50013561597688]
  Retrieval-Augmented Generation enhances large language models by incorporating external knowledge.<n> deploying it in sensitive scenarios risks privacy leakage via malicious prompts.<n>We propose a multi-agent framework that sanitizes retrieved content through semantic rewriting.
  arXiv  Detail & Related papers  (2026-06-23T14:21:41Z)
• ResAgent: Entropy-based Prior Point Discovery and Visual Reasoning for Referring Expression Segmentation [21.87321809019825]
  Referring Expression (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions.<n>textbfmodel is a novel RES framework integrating textbfEntropy-textbfBased Point textbfDiscovery (textbfEBD) and textbfVision-textbfBased textbfReasoning (textbfVBR)<n>model implements a coarse-to
  arXiv  Detail & Related papers  (2026-01-23T01:56:04Z)
• A Multi-Agent LLM Framework for Multi-Domain Low-Resource In-Context NER via Knowledge Retrieval, Disambiguation and Reflective Analysis [7.594209761100934]
  In-context learning (ICL) with large language models (LLMs) has emerged as a promising paradigm for named entity recognition (NER) in low-resource scenarios.<n>We propose KDR-Agent, a novel multi-agent framework for in-context NER that integrates knowledge retrieval, Disambiguation, and Reflective analysis.<n>Experiments across ten datasets from five domains demonstrate that KDR-Agent significantly outperforms existing zero-shot and few-shot ICL baselines.
  arXiv  Detail & Related papers  (2025-11-24T13:23:34Z)
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning [58.16354555208417]
  PAD and FFD are proposed to protect face data from physical media-based Presentation Attacks and digital editing-based DeepFakes, respectively.<n>The lack of a Unified Face Attack Detection model to simultaneously handle attacks in these two categories is mainly attributed to two factors.<n>We present a novel Visual-Language Model-based Hierarchical Prompt Tuning Framework that adaptively explores multiple classification criteria from different semantic spaces.
  arXiv  Detail & Related papers  (2025-05-19T16:35:45Z)
• PS-ReID: Advancing Person Re-Identification and Precise Segmentation with Multimodal Retrieval [38.530536338075684]
  Person re-identification (ReID) plays a critical role in applications such as security surveillance and criminal investigations.<n>We propose bf PS-ReID, a multimodal model that combines image and text inputs to enhance ReID performance.<n> Experimental results demonstrate that PS-ReID significantly outperforms unimodal query-based models in both ReID and segmentation tasks.
  arXiv  Detail & Related papers  (2025-03-27T15:14:03Z)
• Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification [31.065557919305892]
  Unsupervised person re-identification (Re-ID) has received increasing research attention. Most clustering-based methods take each cluster as a pseudo identity class. We propose to split each single cluster into multiple proxies according to camera views.
  arXiv  Detail & Related papers  (2022-01-15T10:12:03Z)
• Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification [123.75412386783904]
  State-of-the-art object Re-ID approaches adopt clustering algorithms to generate pseudo-labels for the unlabeled target domain. We propose an uncertainty-aware clustering framework (UCF) for UDA tasks. Our UCF method consistently achieves state-of-the-art performance in multiple UDA tasks for object Re-ID.
  arXiv  Detail & Related papers  (2021-08-22T09:57:14Z)
• Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification [51.98150752331922]
  Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. We propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase. Our method outperforms the state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2020-12-26T07:35:35Z)
• Camera-aware Proxies for Unsupervised Person Re-Identification [60.26031011794513]
  This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. We propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera. Based on the camera-aware proxies, we design both intra- and inter-camera contrastive learning components for our Re-ID model.
  arXiv  Detail & Related papers  (2020-12-19T12:37:04Z)
• Style Normalization and Restitution for Generalizable Person Re-identification [89.482638433932]
  We design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains. We propose a simple yet effective Style Normalization and Restitution (SNR) module. Our models empowered by the SNR modules significantly outperform the state-of-the-art domain generalization approaches on multiple widely-used person ReID benchmarks.
  arXiv  Detail & Related papers  (2020-05-22T07:15:10Z)

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.