MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection

• URL: http://arxiv.org/abs/2602.02222v1
• Date: Mon, 02 Feb 2026 15:28:17 GMT
• Title: MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection
• Abstract summary: High-fidelity generative models have narrowed the perceptual gap between synthetic and real images, posing serious threats to media security.<n>Most existing AI-generated image (AIGI) detectors rely on artifact-based classification and struggle to generalize to evolving generative traces.<n>We propose MIRROR, a framework that explicitly encodes reality priors using a learnable discrete memory bank.
• Score: 31.416844677021615
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-fidelity generative models have narrowed the perceptual gap between synthetic and real images, posing serious threats to media security. Most existing AI-generated image (AIGI) detectors rely on artifact-based classification and struggle to generalize to evolving generative traces. In contrast, human judgment relies on stable real-world regularities, with deviations from the human cognitive manifold serving as a more generalizable signal of forgery. Motivated by this insight, we reformulate AIGI detection as a Reference-Comparison problem that verifies consistency with the real-image manifold rather than fitting specific forgery cues. We propose MIRROR (Manifold Ideal Reference ReconstructOR), a framework that explicitly encodes reality priors using a learnable discrete memory bank. MIRROR projects an input into a manifold-consistent ideal reference via sparse linear combination, and uses the resulting residuals as robust detection signals. To evaluate whether detectors reach the "superhuman crossover" required to replace human experts, we introduce the Human-AIGI benchmark, featuring a psychophysically curated human-imperceptible subset. Across 14 benchmarks, MIRROR consistently outperforms prior methods, achieving gains of 2.1% on six standard benchmarks and 8.1% on seven in-the-wild benchmarks. On Human-AIGI, MIRROR reaches 89.6% accuracy across 27 generators, surpassing both lay users and visual experts, and further approaching the human perceptual limit as pretrained backbones scale. The code is publicly available at: https://github.com/349793927/MIRROR

Related papers

• LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals [50.157719466558696]
  We show that modern generators exhibit low-rank collapse in the semantic-residual subspace while preserving the dominant semantic direction.<n>We propose textbfLoRC, a framework that decouples semantic dominance to capture the collapsed residual geometry.<n>Our method improves accuracy by an average of 7.0% across multiple benchmarks and achieves 97.0% accuracy on 39 unseen generators.
  arXiv  Detail & Related papers  (2026-08-21T08:58:47Z)
• Ghosts Beneath Textures: Texture-Relation Cues for Cross-Paradigm AI-Generated Image Detection [33.4849821487505]
  ConImageGen is a benchmark for cross-paradigm AI-generated image detection.<n>By suppressing semantic interference, we visualize, for the first time, semantics-irrelevant texture patterns across generation paradigms.<n>We propose DTS-Det, a framework that captures and leverages such relations for generalized AI-generated image detection.
  arXiv  Detail & Related papers  (2026-07-04T13:08:01Z)
• Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection [80.15317858033534]
  ForeAgent is an agentic forensics framework for AI-generated image detection with iterative self-evolution.<n>ForeAgent achieves state-of-the-art performance on the Chameleon benchmark, reaching 82.18% accuracy.<n>ForeAgent produces more consistent and causally grounded reasoning compared to GPT-5 and GPT-5-mini.
  arXiv  Detail & Related papers  (2026-06-25T02:59:33Z)
• On Improving Robustness of Deepfake Image Detectors [5.7418146925786795]
  We propose a unified framework that integrates three complementary design principles.<n> adversarial attacks primarily operate on low-order statistics and visual semantics.<n>Our method consistently improves robustness across six architecturally diverse detectors.
  arXiv  Detail & Related papers  (2026-06-01T19:03:32Z)
• DNA: Uncovering Universal Latent Forgery Knowledge [39.19379714306656]
  forgery detection capability is already encoded within pre-trained models.<n>DNA framework employs a coarse-to-fine excavation mechanism.<n>Hifi-Gen is a high-fidelity synthetic benchmark built upon the very latest models.
  arXiv  Detail & Related papers  (2026-01-30T03:48:30Z)
• Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection [95.08316274158165]
  X-AIGD provides pixel-level, categorized annotations of perceptual artifacts, spanning low-level distortions, high-level semantics, and cognitive-level counterfactuals.<n>Existing AIGI detectors demonstrate negligible reliance on perceptual artifacts, even at the most basic distortion level.<n>Explicitly aligning model attention with artifact regions can increase the interpretability and generalization of detectors.
  arXiv  Detail & Related papers  (2026-01-27T10:09:17Z)
• CINEMAE: Leveraging Frozen Masked Autoencoders for Cross-Generator AI Image Detection [25.84217122259626]
  CINEMAE adapts the core principles of text detection methods to the visual domain.<n>We trained exclusively on Stable Diffusion v1.4, our method achieves over 95% accuracy on all eight unseen generators in the GenImage benchmark.<n>This demonstrates that context-conditional reconstruction uncertainty provides a robust, transferable signal for AIGC detection.
  arXiv  Detail & Related papers  (2025-11-09T11:05:45Z)
• Bi-Level Optimization for Self-Supervised AI-Generated Face Detection [56.57881725223548]
  We introduce a self-supervised method for AI-generated face detectors based on bi-level optimization.<n>Our detectors significantly outperform existing approaches in both one-class and binary classification settings.
  arXiv  Detail & Related papers  (2025-07-30T16:38:29Z)
• Fair Deepfake Detectors Can Generalize [51.21167546843708]
  We show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions.<n>Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals.<n>DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art
  arXiv  Detail & Related papers  (2025-07-03T14:10:02Z)
• RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors [57.81012948133832]
  We present RAID (Robust evaluation of AI-generated image Detectors), a dataset of 72k diverse and highly transferable adversarial examples.<n>Our methodology generates adversarial images that transfer with a high success rate to unseen detectors.<n>Our findings indicate that current state-of-the-art AI-generated image detectors can be easily deceived by adversarial examples.
  arXiv  Detail & Related papers  (2025-06-04T14:16:00Z)
• Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection [11.907536189598577]
  Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators.<n>We trace this failure in part to latent prior bias: detectors learn shortcuts tied to patterns stemming from the initial noise vector rather than learning robust generative artifacts.<n>We propose On-Manifold Adversarial Training (OMAT), which generates adversarial examples that remain on the generator's output manifold.
  arXiv  Detail & Related papers  (2025-06-01T07:20:45Z)
• Towards Generalizable Forgery Detection and Reasoning [23.858913560970866]
  We formulate detection and explanation as a unified Forgery Detection and Reasoning task (FDR-Task)<n>We introduce the Multi-Modal Forgery Reasoning dataset (MMFR-Dataset), a large-scale dataset containing 120K images across 10 generative models, with 378K reasoning annotations on forgery attributes.<n>Experiments across multiple generative models demonstrate that FakeReasoning achieves robust generalization and outperforms state-of-the-art methods on both detection and reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-27T06:54:06Z)
• Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection [58.87142367781417]
  A naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked.<n>One potential remedy is incorporating the pre-trained knowledge within the vision foundation models to expand the feature space.<n>By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning fake patterns.
  arXiv  Detail & Related papers  (2024-11-23T19:10:32Z)
• HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance [80.97360194728705]
  AbHuman is the first large-scale synthesized human benchmark focusing on anatomical anomalies. HumanRefiner is a novel plug-and-play approach for the coarse-to-fine refinement of human anomalies in text-to-image generation.
  arXiv  Detail & Related papers  (2024-07-09T15:14:41Z)
• RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection [60.960988614701414]
  RIGID is a training-free and model-agnostic method for robust AI-generated image detection. RIGID significantly outperforms existing trainingbased and training-free detectors.
  arXiv  Detail & Related papers  (2024-05-30T14:49:54Z)

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.