AI-Generated Image Detection

Overview

The field studies how to distinguish authentic photographs and artwork from fully generated images and AI-edited content, sometimes also locating altered regions or identifying the source generator. Detectors use visual artifacts such as noise, color and frequency patterns, and local texture, as well as features from pretrained vision models; other approaches compare images with reconstructions or perturbations, or combine several detectors. Researchers evaluate these methods on cross-generator and cross-dataset benchmarks, including tests with compression, resizing, and other real-world changes, and increasingly on specialized content such as documents and scientific figures. A central challenge is that strong results on familiar, clean benchmarks often fail to transfer to new generators or settings, while improving sensitivity can raise false alarms on genuine images.

Latest papers

203 papers13 papers in the last four weeks, down 35% on the four weeks before. 0.1% of all new papers.

Nov 12, 2026

DEDCA: Test-Time Adaptation for Generalized AI-Generated Image Detection

AI-generated image detectors face significant challenges when deployed in real-world environments, particularly when test samples are produced by unseen generators that deviate from the source training distribution. Existing detectors often rely on a single type of evidence, such as semantic representations or low-level generation traces, making them vulnerable when the corresponding cue becomes unreliable. Moreover, adapting detectors to newly emerging generators usually requires target labels or retraining, which is costly and impractical. To address these challenges, we propose Dual-Evidence Disagreement-Constrained Adaptation (DEDCA), a test-time adaptation framework for generalized AI-generated image detection. DEDCA constructs a dual-evidence detector by combining CLIP-based semantic evidence with trace evidence extracted from shuffled entropy and residual statistics, and introduces a reliability-aware gate to perform sample-specific adaptive fusion. Our key idea is to exploit the disagreement between the two evidence streams as an unlabeled adaptation signal, enabling the detector to adjust to target-domain shifts without relying on target labels or blindly trusting a single prediction stream. Experiments show that DEDCA achieves superior performance on the GenImage benchmark by outperforming state-of-the-art AI-generated image detectors and test-time adaptation methods with 92.0% average accuracy.
Nov 11, 2026

From Pixels to Prompts: Physics-Guided Language Enhancement for AI-Generated Image Detection

AI-generated content (AIGC) has substantially narrowed the visual gap between natural and synthetic images, while existing detectors often rely on generator-specific artifacts and exhibit limited generalization to unseen models. This motivates a fundamental question: which intrinsic physical image characteristics provide stable, discriminative cues for distinguishing natural from AI-generated images? We investigate this by systematically identifying robust physical features and incorporating them into a vision-language representation without external textual prompts at inference. We first analyze 15 handcrafted physical descriptors across images from over 20 generative models. Based on cross-generator stability and real-fake discriminability, we propose a Feature Stability-Discriminability Validation Assessment (FSDVA) to select a compact set of reliable features. Five core features, including Laplacian variance, Sobel statistics, and residual-noise variance, are then used to construct structured textual descriptions encoding physical evidence for CLIP-based learning. We integrate these physics-enriched descriptions with image representations via a native physics-guided multimodal framework, adapting CLIP ViT-L 14 with LoRA. At inference, the model requires only the input image, with no external captions or manual prompts. On GenImage, our method achieves 99.0 percent accuracy on SDv1.4 and 96.7 percent on Wukong, with a mean of 97.23 percent across eight generative models versus 95.8 percent for C2pCLIP under the same setting. On UniversalFakeDetect, it maintains strong, stable generalization across diverse and unseen generation settings. These results show that carefully selected physical image statistics provide complementary forensic evidence to pretrained vision-language representations, enabling interpretable, more generator-agnostic AIGC detection.
Nov 3, 2026

Learning to Falsify: Hierarchical Multiple Instance Learning for High Resolution AI-Generated Image Detection

Recent advances in generative models have made synthetic images increasingly photorealistic, posing growing challenges to reliable and generalizable detection of AI-generated images. Existing methods typically rely on holistic image-level classification, which may overlook local artifacts, especially in high-resolution images. To address this limitation, we formulate this task as a falsification-driven multiple instance learning problem, where a single fake patch can falsify the whole image, while a real image requires all patches to be authentic. Based on this formulation, we propose Learning to Falsify (LTF), a hierarchical multiple instance learning framework that models an image as multiple bags of instances across different spatial levels and aggregates their predictions under the falsification-inspired principle. We further introduce Cross-Shuffle during training to encourage the model to learn local artifact evidence rather than image-level shortcuts. Furthermore, we propose the Falsification-driven Test-time Aggregation Strategy (FATAS), a plug-and-play module that extends the same falsification-inspired principle to existing detectors by aggregating patch-level predictions. Extensive experiments demonstrate that LTF achieves strong generalization and robustness across multiple benchmarks, while FATAS substantially improves representative detectors in high-resolution scenarios without retraining. Code is available at https://github.com/HuiGuanLab/LTF.git
Nov 3, 2026

Generalizable AI-Generated Image Detection with Embedding-Space Explanations

AI-generated images have reached unprecedented realism, while instruction-driven AI editors re-synthesize images for local changes, leaving no splice boundary to localize. Most detectors are black boxes with unverifiable verdicts and generalize poorly because adapting a backbone on the detection distribution memorizes generator-specific fingerprints that quickly become obsolete. Specialist detectors built on pure-vision representations, particularly DINOv3, generalize well across generators, but explainable methods forgo this advantage: jointly training one multimodal model for classification and language generation subjects its visual representation to the language objective. We therefore require that explanation training cannot alter the verdict. We introduce FOX, which first builds and locks a specialist DINOv3 detector, then uses its representation to guide a lightweight VLM toward forensic explanation. A joint-embedding predictor maps locked visual evidence into a frozen text encoder's semantic space, producing guidance that the VLM verbalizes on demand. FOX achieves 97.4 mean AUC across 14 unseen generators, 69.8 BERTScore on XPlainVerse, and 56.1 on LOKI.
Oct 28, 2026

The Search for Statistical Indistinguishability Between Real and Fake Images

Images produced by generative models appear strikingly similar to real ones. In this work, we study whether perfection has been reached by generated content in terms of matching the properties of real data. We train deep neural networks to separate real data from fake and observe their test accuracies. Only a chance performance has any scope of proving statistical indistinguishability. However, since generative models are known to sometimes introduce small errors, e.g., low level checkerboard artifacts, we create progressive abstractions of the original real/fake images to potentially bring them to a space where those artifacts get wiped away. These include operations such as blurring, downsizing, cropping, converting RGB images into edge/semantic maps, etc. To our surprise, almost none of the abstractions are able to make fake data indistinguishable from real. The only cases when neural network based classifiers fail to separate the two categories is when the data is abstracted to such an extent that the original content seems mostly lost to the human eye, e.g., downsizing a 256×256256 \times 256 RGB image of human face to 4×44 \times 4 resolution. We observe this trend across four different datasets of varying complexity (MNIST, CelebA, FFHQ and GenImage) and across various types of generative models (GANs, VAEs, diffusion models). This shows that the nature of fake artifacts extends all the way from low level to very high level in images. The simple implication is that fake images are much more different from real than we are used to think.
Oct 28, 2026

Enhanced image forensics through partial C2PA-based provenance information

Cryptographically verifiable C2PA-based Content Credentials (CCs) can be attached to freshly acquired or generated digital images but also to already existing ones with no previous provenance information, for instance after processing through trusted C2PA-enabled software tools. The latter case leads to images with so-called partial CCs, which capture only the last operations applied, while prior provenance remains unknown and can be investigated through signal forensics. This paper addresses the forensic analysis of such images, highlighting the opportunity to leverage the partial CCs as additional trusted knowledge to adapt forensic detectors towards the statistical characteristics of the image under analysis and mitigate potential distribution shifts. To this end, a two-step strategy is envisioned: (i) reconstructing the operations applied by the last signer through a structural analysis of the partial CCs; (ii) exploiting the obtained reconstruction to enhance the forensic detector of the analyst through an adaptation process. An empirical analysis on partial CCs produced by commercial C2PA-enabled software tools through different editing operations is carried out, providing evidence on the feasibility of the reconstruction in practical cases. An experimental case study on the forensic task of synthetic image detection is then presented, showing that the proposed strategy can significantly enhance the performance of state-of-the-art detectors on test images that are postprocessed via C2PA-enabled software tools after being generated/acquired.
Oct 22, 2026

WildFakeToolBench: Benchmarking AI-Generated Image Detectors with Web-Sourced Image Processing

As AI generated images are getting popular these days, discussions on such generations are widely existed in current public forums, software repositories, and photography tutorials. Moreover, with the help of LLM-assisted code translation, malicious actors can adopt such information to evade detectors without specialized knowledge or local GPU execution of the resulting tools. To evaluate such risks, we introduce WildFakeToolBench, a benchmark suite of 156156 executable image-processing tools derived from 220220 public sources across 142142 domains. Each tool retains its source evidence and passes syntax, execution, and output-distortion checks without using feedback from the evaluated detectors. On 105105 generated images from five generators, we evaluate six state-of-the-art detectors with images processed by the tools in our collected bench to assess their effectiveness against such in-the-wild risks. The strongest individual tools achieve attack success rates of 25.25%25.25\%--100%100\% across detectors, exceeding the strongest of six selected image-processing baselines for each detector. Evaluating subsets of an eight-tool pool yields worst-case coverage above 80%80\% for every detector. Effectiveness is sparse and detector-specific: high coverage across candidates does not imply reliable one-shot evasion. These findings not only highlight the potential of such web-sourced risks, but also show the potential on establishing AI-image detector robustness evaluation framework based on those in-the-wild information.
Oct 21, 2026

From Augmentation to Synthetic Evidence: Evaluating Generated Chest Radiographs at Dataset Intake

While generated chest radiographs can serve as valuable data augmentation when explicitly declared, the same pixels become unsupported evidence when submitted as records of real clinical examinations. We study this dataset-intake vulnerability by disentangling three questions: (1) whether an image passes an automated technical quality check, (2) whether an origin classifier flags it as synthetic, and (3) whether a trusted provenance record supports the claimed clinical acquisition. In this study, a submitter uses Qwen3.8-27B to select up to 20 candidate radiographs from pools of 1,000 Cheff-identified or SynthCheX images, while a receiver evaluates image quality via MedGemma 1.5 and predicts origin using a linear probe over frozen DINOv3 features. Although quality selection increases MedGemma quality passes from 12/20 to 19/20 for Cheff-identified images and from 8/20 to 17/20 for SynthCheX, we find no evidence that candidate selection increases passage through both checks simultaneously: zero selected Cheff-identified images pass both gates, and uniform, quality-guided, and surrogate-guided selection yield 2, 1, and 2 SynthCheX passes out of 20, respectively. On unprocessed test cohorts, the origin classifier rejects 4,677 of 5,000 SynthCheX images at a nominal 5% false-alarm rate (flagging 110 of 2,297 real NIH radiographs), yet leaves 152 SynthCheX images that pass both pixel-level checks. Moreover, pixel-level screening is fragile to routine distribution shifts: JPEG compression reduces SynthCheX-versus-NIH AUROC from 0.987 to 0.841, and applying the NIH-calibrated threshold to an external genuine cohort (Open-I) triggers false alarms on 568 of 957 authentic radiographs (59.4%). Because pixel-level checks can filter submissions but cannot verify clinical acquisition claims, we argue that dataset intake pipelines must record and verify source provenance independently of image pixels.
Oct 21, 2026

HumanCentric-Scenes-AI: A Human-Curated Multimodal Dataset of AI-Generated Human-Centric Scenes Across Surveillance, Occupational Portraits, AI-Edited Images, and Short-Form Video

We introduce HumanCentric-Scenes-AI, a human-curated dataset of 296 AI-generated stimuli that depict people across four contexts in which people encounter AI-generated media. The Surveillance subset contains 85 AI-generated CCTV-style images. The Occupations subset contains 128 AI-generated occupational portraits in a balanced paired design covering 64 occupations with one female and one male version of each. The AI-edited subset contains 27 real photographs in which a region was altered or replaced by a generative model. The Video subset contains 56 AI-generated short videos. We curated the images and videos manually over multiple rounds to make them as photorealistic as possible. For each stimulus we release the file, the generation prompt where recorded, and per-stimulus metadata. We report depicted-gender distributions from an initial set of 134 generations without a specified gender and compare them with U.S. Bureau of Labor Statistics occupational gender shares. We report edit-region size and its association with zero-shot detection difficulty for the AI-edited subset. We report image-quality distributions for the Surveillance subset and subject-category coverage for the Video subset. HumanCentric-Scenes-AI is intended first for human-perception research, and also for calibration of AI-detection classifiers and bias analysis of generative models.
Oct 20, 2026

WildAIGC-Bench: Can AI Image Detectors Handle the Wild? A Benchmark of Generated and Edited Images in Online Circulation

AI-generated images linked to news events and online claims can mislead audiences, enable fraud, or cause public controversy. We introduce WildAIGC-Bench, built through recurring collection across news websites, fact-checking sources, and related social media content. The pipeline combines broad coverage, timely updates, and human-verified labels through scheduled discovery, automatic screening and preliminary annotation, and human review of image-specific evidence. The benchmark contains 407 verified AI-generated or edited images, each accompanied by a source webpage link and an evidence summary. Images retain the conditions encountered online, including compression, screenshots, and recapture. Evaluation of dedicated visual detectors, multimodal large language models, and a simple Perception Encoder baseline reveals substantial recall gaps relative to existing benchmarks. WildAIGC-Bench provides both a practical detection challenge and a basis for continued data expansion and source-based verification. The dataset is released at https://github.com/YuZijian/WildAIGC-Bench.
Oct 20, 2026

Media Intelligence Platform: Multimodal Detection of Synthetic and Manipulated Content

The rapid progress of generative artificial intelligence has led to a significant increase in manipulated multimedia content, including synthetic faces, forged videos, AI-generated images, fake audio, and locally edited images. Existing detection approaches are typically designed for a single manipulation type, limiting their applicability in real-world scenarios involving heterogeneous media sources. In this work, we present the Media Intelligence Platform (MIP), a unified web-based framework for multimodal media forensics integrating specialized modules for fake video detection, face morphing detection, AI-generated image detection, audio deepfake detection, localized image manipulation detection, and text analysis. Its modular architecture enables flexible integration of heterogeneous models and supports future extensions for emerging manipulation techniques. Experimental results on representative benchmark datasets demonstrate reliable detection performance across multiple media modalities while providing a practical and user-friendly interface for forensic investigations. The platform highlights the potential of unified multimodal systems for comprehensive deepfake detection in real-world environments, and is accompanied by a public demonstrator released with this workshop submission to support reproducibility and community evaluation.
Oct 18, 2026

Tricking Synthetic Image Detectors with Amortized Generative Attacks

Rapid advances in image synthesis have increased the need for reliable synthetic-image detectors, yet their robustness to transferable attacks remains incomplete and understudied. Existing evaluations generally examine whether an attack constructed against one detector transfers to another, but rarely isolate how its effectiveness changes when the attacked images originate from different generators. We conduct a systematic evaluation of three representative attacks: two iterative perturbation-based methods, MIG and MuMoDIG, and the amortized generative attack Tricker. Across four detectors and five generators spanning diverse architectures, we introduce a two-axis evaluation protocol that independently varies the surrogate detector used to construct or train the attack and the generator supplying its input images. We assess attack effectiveness, cross-detector transferability, perceptual quality, runtime, and interaction with common post-processing operations. We revisit Tricker and show that its data and training requirements can be substantially reduced, enabling broader and more efficient evaluation. Our results demonstrate that transferability is not a detector-only property: the input-generator distribution strongly influences both evasion effectiveness and attacked-image quality. MIG and MuMoDIG exhibit pronounced dependence on the detector--generator pair, whereas Tricker provides more uniform white-box evasion and image quality. We additionally observe that post-processing maintains the asymmetric transferability topology. These findings expose a neglected dimension of attack evaluation and motivate transfer-aware protocols that jointly account for detector and generator variation. We will release our code, evaluation data, and trained attack models with a responsible-use statement.
Oct 16, 2026

Can We Use Saliency Maps for the Evaluation of Generative Image Models?

Evaluating generative image models remains challenging, as commonly used metrics depend on fixed pretrained feature extractors optimized for different tasks that do not always align with human realism perception across datasets and model families. To address this limitation, we investigate a human-inspired evaluation framework that avoids representations learned for unrelated tasks. Specifically, we train a generator-specific classifier to distinguish real images from samples produced by a given model and analyze its decisions using saliency maps. Across diverse benchmarks, we observe that these classifiers learn generator-specific artifacts rather than a universal notion of "fakeness", exhibiting strong accuracy and limited cross-generator transfer. This makes saliency analysis particularly informative: the resulting attribution maps highlight visual cues and structural irregularities characteristic of each model's outputs. By combining classification accuracy and saliency information, we obtain a composite score aligned with human judgments, without relying on large pretrained backbones and using only real and generated samples from the evaluated model.
Oct 15, 2026

Beyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial Images

As image generation models become increasingly capable of producing highly realistic content, traditional forensic techniques are struggling to keep up. This paper investigates whether MLLMs can instead be used as a form of forensic analysis by identifying synthetic media. Specifically, the study aims to determine whether these models detect fake images by recognising physical inconsistencies, or whether they rely on digital artefacts such as embedded watermarks. Six MLLMs (GPT-4o, GPT-5, GPT-5.2, Gemini 2.5, Gemini 3, and Seed 1.6) are benchmarked using a dataset of 400 images. Fifty images are authentic photographs, while the remaining 350 are generated using seven leading image models: Gemini 3, Gemini 2.5, Flux.2 Pro, GPT-Image-1, GPT-Image-1.5, Seedream 4.0, and Seedream 4.5. The evaluation is structured in three stages: single-image classification, pairwise comparison, and a focused "self-detection" experiment on Gemini. Several MLLMs achieved a high detection accuracy, with GPT-5.2 reaching a peak of 97.9% in the pairwise experiment, against specific generators and an overall mean pairwise accuracy of 82.5% by identifying structural or physical inconsistencies within images. However, results from the self-detection experiment indicate that the presence of invisible SynthID watermarks leads to a 10% reduction in Gemini's detection accuracy compared to the clean control group. One possible explanation is that SynthID embedding reduces some of the visible artefacts the models rely on for detection. These results imply that MLLMs can detect structural artefacts without relying on watermarks, but performance varies substantially across model generations. The findings also suggest that SynthID embedding may suppress some of the structural artefacts used during detection.
Oct 13, 2026

COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection

Generalizable AI-generated image (AIGI) and deepfake detection remain challenging due to the asymmetry phenomenon, where adaptation to limited training distributions can degrade the transferable representations of Vision Foundation Models (VFMs). Recent subspace adaptation methods mitigate this issue by freezing high-magnitude principal components while adapting the residual subspace. However, such magnitude-based decomposition is data-agnostic and does not explicitly account for target-relevant semantics, potentially leading to semantic misalignment. We propose COMPASS (COntextual Moment Prior Alignment for Subspace Separation), a data-aware subspace adaptation framework that uses a small unlabeled Semantic Proxy Set to estimate target activation statistics. COMPASS incorporates activation covariance into the decomposition of pre-trained weights, preserving target-relevant representations as a stable semantic reference while the residual adapter learns forgery-related variations. The proxy calibration requires no gradient-based optimization. Extensive experiments demonstrate strong generalization across cross-dataset, cross-method, joint cross-dataset-method, and open-world cross-generator evaluations, achieving state-of-the-art performance on both Deepfake and AIGI detection benchmarks.
Oct 8, 2026

Relative Patch Response Learning for Generalizable AI-Generated Image Detection

Generative models can now synthesize highly realistic images, simultaneously increasing the risks of misinformation and visual forgery. Therefore, detecting AI-generated images becomes more essential, and a reliable detector must generalize to unseen generators and stay robust to unseen perturbations in the wild. Existing detectors are typically trained on either independently collected real and generated images or aligned real-generated pairs designed to mitigate content bias. Building on aligned pairs, recent methods form a mixed view by replacing some patches of the real image with their generated counterparts. However, we find that self-attention lets real and generated patches interact, so the feature of each patch no longer reflects its own source alone. This contextual shift makes a per-patch source label an imprecise target. To this end, we propose Relative Patch Response Learning (PRL). Instead of labeling each patch, PRL compares the same patch across two mixed views of an aligned pair and learns from its patch response, the change of its score between the views. (i) To give precise supervision under the contextual shift, a relative response objective measures the responses of source-changed patches against those of source-unchanged patches, which respond to the shift alone. (ii) To provide a reliable reference for the shift, a reference coherence objective keeps each group of source-unchanged patches moving as a whole. (iii) Since the two views contain different amounts of generated content, an area ranking objective asks the view with the larger generated area to have a higher mean patch score. Extensive experiments demonstrate the superior performance of PRL, which surpasses the best prior methods by 4.3% and 5.9% in average balanced accuracy across eight standard and three in-the-wild benchmarks, respectively.
Oct 8, 2026

EvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection

AI-generated image detectors are commonly trained on fixed generator domains and become difficult to maintain as new generative models emerge. Continual adaptation is challenging because replaying historical generated images is costly, whereas updating shared parameters with limited current-domain data can overwrite prior forensic knowledge. We propose EvoKnow, a replay-free framework that formulates continual AI-generated image detection as forensic knowledge evolution. EvoKnow preserves a shared forensic basis learned from base domains, incrementally adds isolated residual experts for complementary generator-relevant evidence, and retrieves expertise through an Analytical Incremental Router (AIR) updated in closed form from current-stage generated images and accumulated sufficient statistics. Experiments demonstrate effective cross-generator generalization, few-shot expansion, and long-horizon continual adaptation. With ten generated images per arriving generator, EvoKnow achieves 96.70% average accuracy on non-base GenImage generators and 94.48% accuracy on Chameleon without target-benchmark adaptation. Under a strict replay-free continual learning protocol, EvoKnow achieves state-of-the-art continual learning performance, attaining 96.32% mean stage-wise accuracy and 4.32% average forgetting.
Oct 6, 2026

Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection

As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existing methods primarily rely on task-specific supervision to adapt vision foundation model representations, without fully exploiting internal forensic knowledge to guide detection. To address this limitation, we propose Reserve-Guided Elicitation (RGE), a framework that treats sparse, origin-sensitive internal components in pretrained models as a forensic reserve and translates their localization into structural constraints for lightweight adaptation. Specifically, we first use the Forensic Lens (F-lens) to decompose activations across layers and token groups into independent components and globally screen them by their response differences between real and generated images, identifying reserve sites and directions. Next, we map the selected directions back to hidden-state space to construct fixed reserve subspaces and insert Forensic Reserve Adapters (FRA) only at the identified sites. Finally, with the backbone parameters, previously fitted reference classifier, and subspace bases fixed, we train only the FRA coefficient maps to generate input-dependent residual updates constrained to the corresponding subspaces, strengthening existing forensic responses. Using only 500 labeled training images and a trainable parameter budget below 0.2% of the backbone, RGE achieves competitive performance across three detection benchmarks without target-benchmark adaptation. Furthermore, RGE consistently improves over the corresponding frozen detectors across eight encoders spanning self-supervised and vision-language pretraining, eliciting a latent forensic capacity broadly shared across pretrained vision models.
Oct 6, 2026

Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering

AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These routes can produce similar visible artifacts but expose different representations, intervention points, and provenance evidence. We develop a production-centered framework that compares detection and watermarking across both routes. An explicit verification specification distinguishes passive inference, message recovery, and authenticated provenance. We organize image, video, source-code, and rendering-aware watermarks by production stage. We examine the different requirements of generated images and video, plots and SVG, programmable video, and agent-composed workflows. Documented Claude, OpenAI, and rendering-tool interfaces connect the framework to concrete systems. We pose ten scoped research questions on identifiability, observability, fair comparison across stages, recoverable payload, reconstruction, synchronization, composition, hybrid local contribution, and private production-event authentication. The result is a conceptual research agenda grounded in published methods, inspected interfaces, and elementary boundary examples. It reports no experiments and claims no new theorems; its appendix results are elementary calculations, and documentation and source inspection establish interfaces, not empirical robustness.
Oct 5, 2026

Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations

Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, systematic evaluations of their effectiveness against realistic attacks remain limited. We present a systematic evaluation of harmful content generation across five open text-to-image models using an automated pipeline that transforms legitimate news captions into unsafe prompts targeting sexually explicit content, violence/gore, harmful stereotypes, self-harm, and hate speech. We evaluate both standard models with built-in safety mechanisms and community fine-tuned variants that bypass content restrictions. A human evaluation of 1,500 generated images shows high harmful-content generation rates: 89.2% for gore-related prompts, 47.6% for sexually explicit content, 43.6% for harmful stereotypes, 46.0% for hate speech, and 34.5% for self-harm, predominantly through graphic violence. Models show substantial capability for generating violent and stereotypical content, while community fine-tuned variants are particularly vulnerable to sexually explicit prompts. Generation quality is largely preserved under harmful prompting, producing imagery of sufficient fidelity to pose risks for disinformation and abuse; FLUX.1-dev produces clearly realistic harmful images in 30.9% of cases. We further evaluate automated moderation systems and find substantial detection gaps that allow unsafe images to evade filtering. Finally, we assess synthetic image detectors and show that models trained only on benign datasets perform worse on explicit content, while more diverse training data improves detection, highlighting semantic distribution gaps in current approaches. These findings expose limitations in current generation safeguards, moderation systems, and synthetic image detection, highlighting the need for stronger defenses against misuse at scale.
Sep 30, 2026

Typographic Attack Against VLM-based AI-generated Image Detection

Vision-language models (VLMs) are increasingly used for AI-generated image (AIGI) detection, providing natural-language explanations for authenticity judgments. However, their ability to interpret text within images may also expose these judgments to misleading semantic cues. We systematically evaluate typographic attack strategies across detection-oriented, open-weight, and commercial VLMs, considering both real-to-fake and fake-to-real attacks. Our results show that reasoning modes generally exhibit greater vulnerability than direct modes and that attack effectiveness exhibits pronounced directional asymmetry. Moreover, larger models tend to exhibit higher clean detection accuracy but also higher attack success rates. We further examine attack robustness under image and text transformations and investigate whether overlays indicating the correct class can aid error correction. Together, these analyses characterize how typographic attacks influence authenticity judgments and expose limitations of current VLM-based AIGI detection systems.
Sep 29, 2026

Look Closer: Patch-wise Supervision for AI-Generated Image Detection

How much of an image does a detector need to see? Small RGB regions can retain useful evidence of image synthesis even when they reveal little of the full scene. Motivated by single-patch detection, we study patch-wise supervision: a shared backbone classifies explicit crops, each crop receives its own loss, and patch probabilities are averaged only at inference. The procedure requires neither handcrafted residual filtering nor a learned image-level fusion module. Experiments span single-patch selection, multiple generator collections, and four CNN and Transformer backbones. On GenImage, the reported patch-wise variants improve average accuracy over their whole-image counterparts across all four backbones. Comparisons of supervision granularity, source resolution, crop size, and inference coverage further characterize the approach, while post-processing tests and difficult-image evaluation reveal its limitations. The historical experiments include evaluation-based model selection, so their scores are not presented as a uniformly selected leaderboard comparison. Overall, the study identifies explicit local input and patch-level supervision as a simple, useful combination for investigating generalizable AI-generated image detection.
Sep 29, 2026

A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System

Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to evaluate. Surveillance frames, dashcam stills, and phone photographs may be used to establish presence, sequence, causation, damage, or identity, yet contemporary generative systems allow non-experts to alter or fabricate such images through ordinary prompt-based interfaces. Existing image-forensics benchmarks provide important resources for face manipulation, classical tampering, and general synthetic-image detection, but they are not organized around the forms of visual evidence submitted in courts, the localized edits that can change what an exhibit appears to prove, or the consumer-tool threat model now facing the justice system. We introduce the CIFAR Synthetic Evidence Corpus for Detecting AI-Manipulated Images, a benchmark for evidentiary image authentication in court and justice-system contexts. The corpus contains 1,505 photographic items, including 720 authentic controls and 785 manipulated or fabricated images, spanning surveillance, dashcam, and consumer-photo imagery. Manipulations are organized into scene-condition edits, localized element edits, and full fabrications produced with contemporary generative systems. Each item is released with structured metadata covering source provenance, manipulation tier, subtype, generator, prompt template, and scene attributes, enabling controlled evaluation beyond aggregate binary detection. We also establish baselines with publicly available image-manipulation detectors, showing that current systems exhibit error profiles that remain problematic for evidentiary use. The dataset, prompts, metadata, code, and baseline evaluation scripts are released to support research on visual evidence authentication, information integrity, and trustworthy AI for the justice system.
Sep 29, 2026

RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detection

The rapid evolution of image generators calls for forensic cues that generalize beyond known generation mechanisms. Existing detectors often rely on static image representations or endpoint reconstruction discrepancies, leaving the evolution of intermediate reconstruction stages underexplored. We observe that the relative token predictability of real and generated images can reverse across reconstruction scales, suggesting that intermediate stages may expose forensic evidence overlooked by endpoint comparisons. Motivated by this observation, we propose RED (Reconstruction Evolution Dynamics), a framework that captures transferable forensic cues from coarse-to-fine reconstruction evolution. To our knowledge, RED is the first framework to use scale-wise token predictability to guide forensic evidence aggregation across intermediate reconstruction states. It represents the reconstruction trajectory produced by a frozen multiscale VQ-VAE in the shared feature space of a frozen CLIP encoder. To connect the observed predictability variations with visual evidence, RED learns image-adaptive stage weights from scale-wise token negative log-likelihoods provided by a frozen VAR model. A cross-stage evidence aggregation module then jointly models the original-image representation and the weighted reconstruction features, capturing complementary forensic cues through interactions along the reconstruction trajectory. Experiments on six diverse benchmarks demonstrate that RED achieves the highest average accuracy of 92.5% and average precision of 97.5% among the evaluated methods. Further evaluations show strong robustness to common image degradations, supporting the value of reconstruction evolution for generalizable AI-generated image detection. The code will be made publicly available upon acceptance of this paper.
Sep 27, 2026

MAD-Guard: Controlled Study of Autoregressive Generation versus Direct Decision Interfaces for Closed Multimodal Forensic Tasks

When should multimodal foundation models generate tokens, and when should they directly output a decision? We present MAD-Guard, a controlled study of output-decision interfaces for closed multimodal forensic tasks. Once a multimodal representation is computed, is autoregressive generation necessary for closed forensic decisions with high input complexity but low output entropy? Under a matched Qwen3-VL-8B backbone, 2,400 FakeClue training samples, and LoRA budget (r=16,α=32r=16, α=32) on Huawei Ascend 910C NPUs, we evaluate a progression of decision interfaces (AR-SFT [generate] →\to Logit Slice →\to Binary Direct Head →\to +choice →\to +act →\to CLM-Head) and decompose latency into backbone representation (53.12 ms), 151,643-way vocabulary projection (+85.04 ms →\to 138.16 ms), and decoding (+248.26 ms →\to 386.42 ms). Under 1-to-1 binary supervision (LBCE\mathcal{L}_{\mathrm{BCE}}), a Binary Direct Head cuts latency by 2.60×2.60\times-7.27×7.27\times (53.12 ms) and lowers calibration error by 1.88×1.88\times (ECE = 0.0450 vs. 0.0845), with a -1.80% accuracy trade-off (93.10% vs. 94.90%; 0.9795 vs. 0.9871 ROC-AUC) from forfeiting token priors. Gains above AR-SFT arise either from multi-task attribution and uncertainty gating (+choice+act: 96.44% accuracy, 0.9940 ROC-AUC, 0.0187 ECE at 53.71 ms) or from a disaggregated contrastive head (CLM-Head: 96.55% binary and 96.44% multi-task accuracy, 0.0166 ECE, 98.79% 7-class attribution at 54.42 ms) retaining semantic priors without token decoding. Across 5,000 out-of-sample images from five benchmarks, our framework excels on synthetic, camouflage, and document forgeries (96.44% GenImage, 97.73% Chameleon, 91.84% Doc) while showing a clear boundary on compressed face manipulation (FF++ ROC-AUC = 0.5913).
Sep 26, 2026

REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection

AI-generated image detectors are often evaluated on benchmarks where real and synthetic images differ in content, quality, or generation artifacts, allowing models to rely on dataset-specific cues and fail on unfamiliar generators or processed images. Existing datasets provide limited support for evaluating these challenges jointly across diverse visual content. We introduce REALIS, a dataset of 1.43 million real and synthetic images generated by 42 modern text-to-image models, including the latest proprietary systems such as Nano Banana 2. REALIS combines prompts derived from real images, quality filtering, and stratified sampling to reduce class-specific shortcuts while preserving content diversity. We further introduce REALIS-Expert, a stress-test subset for high-quality synthetic images, where real and generated samples are selected with closely matched semantic and visual characteristics. We also propose a robustness protocol covering 35 transformations at five severity levels to analyze detector behavior under image processing. Based on REALIS, our benchmark evaluates pretrained detectors, fine-tuned models, and zero-shot vision-language models under generator and post-processing shifts. On the hardest processed split, the best pretrained conventional detector achieves 0.550 ROC-AUC, compared with 0.752 for the best REALIS-trained detector. REALIS provides a unified framework for measuring and improving the reliability of AI-image detectors under conditions that better reflect real-world use.
Sep 25, 2026

Forensic Twins: Self-Supervised Residual Learning for AI-Generated Image Forensics

Detectors of AI-generated images are typically trained using samples from all Generative AI architectures they must catch, and struggle as soon as a new architecture emerges. Recent approaches have explored self-supervised pre-training as an alternative solution, yet standard frameworks work against the forensic task, e.g., their augmentations overwrite the micro-statistics of image formation. This paper introduces Forensic Twins, a Self-Supervised Residual Learning (SSRL) framework whose pretext task suppresses macroscopic content availability. Each image is mapped through a frozen, off-the-shelf forensic residual extractor, from which two spatially disjoint crops are drawn. Sharing no pixel, the two views retain minimal semantic structure to align, leaving a redundancy-reduction objective with a predominant common signal: the stationary fingerprint of the image acquisition pipeline. Additionally, Forensic Twins is trained exclusively on real images; no AI-generated image is observed at any stage. Experiments show that Forensic Twins attributes AI generator sources with 56.61% accuracy, i.e., 6.13% above the previous state-of-the-art zero-shot method at 375x lower latency. We also demonstrate that fitting a Gaussian Mixture Model (GMM) offline using only the real image embeddings extracted from Forensic Twins turns it into a state-of-the-art zero-shot detector, reaching 97.99% AUC across 27 unseen AI generators, including GANs, diffusion models and commercial systems. Code, weights and exact splits will be made publicly available
Sep 25, 2026

Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance

Passive image provenance asks whether pixels alone can reveal where an image came from: a human, an aggregate AI class, or a particular generator. This becomes a robustness problem once a source image can be edited before the verifier sees it. We study the problem as source--target verification under adversarial distribution shift. Our first result gives the exact best-case limit for any image-only verifier: the largest robust target-acceptance gap equals the minimum total-variation distance between the target distribution and the set of attacked source distributions. This quantity depends on the source, target, and edit class, not on the verifier architecture. Our second result explains why deployed public verifiers can fail before this statistical limit is reached. If the verifier can be emulated on the attack region to error ε\varepsilon, then a surrogate black-box attack reaches target acceptance within 2ε2\varepsilon plus optimization error of the white-box optimum; score-revealing logistic and softmax heads over public features are identifiable, and approximate score access gives stable recovery bounds. A finite-state experiment checks the minimax identity where both sides are computable. On same-prompt real/diffusion benchmarks, the evaluated public CLIP verifiers fail under targeted pixel attacks, while a ResNet-18 victim exhibits partial fake-to-real transfer. Binary feedback with abstention reduces measured attack success, but positive empirical gap upper bounds do not establish robustness. These results motivate separate evaluation of the source--target statistical ceiling and the information released by a deployed verifier.
Sep 24, 2026

EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection

The proliferation of photorealistic AI-generated images demands robust detection methods that generalize across diverse generative models. While existing approaches target manipulation-based forgeries with local artifacts, generation-based images (e.g., from diffusion models) lack such traces, posing a fundamental challenge. We observe that generative models prioritize global semantics at the expense of local texture fidelity, making low-texture regions key indicators of synthetic origin. To exploit this, we propose EIB-Net, an Entropy-guided Information Bottleneck Network. EIB-Net introduces a novel Image Entropy (IE) metric to automatically select the most informative (lowest-entropy) patch, then processes it with a Variational Information Bottleneck (VIB) to learn compact, generalizable features. Extensive experiments on DIFF, DiffusionForensics, and GenImage benchmarks demonstrate state-of-the-art performance: EIB-Net achieves 85.7% accuracy using only 2% of training data, outperforming full-image baselines by over 15%, and maintains robust cross-generator generalization (83.5% average accuracy on GenImage). Furthermore, our entropy-guided patch selection (EGPL) consistently enhances diverse backbones (CNNs and Transformers), proving its practical value for data-efficient detection.
Sep 23, 2026

Fusion Under Component Failure: Negative Results and Failure Modes in Ensemble AI-Generated Image Detection

We built an ordinary stacking ensemble for AI-generated image detection -- three open detectors producing five scores, fused by a gradient-boosted meta-learner that treats a detector's failure as missing data -- deployed it, and then evaluated it against three controls it should have faced first. This paper reports what the controls found, including where they overturned our own earlier conclusions. Fusion is worth its cost only when refitted on the target domain. The shipped meta-learner, fitted on a separate corpus, does not beat its best single member on 2000 StyleGAN faces (AUC 0.9896 vs 0.9961; McNemar p = 1.000). But a stacker refitted in-domain beats that member plus a post-hoc calibrator (Delta-AUC = +0.0025, [+0.0014, +0.0038]; p = 3.4e-4). An earlier draft claimed the calibrated single detector won outright; that comparison mixed regimes and we correct it here. One corpus is not an evaluation. On 80 screenshots every model's AUC interval contains 0.5. We can say nothing stronger: the difference between the ensemble's drop and its best member's is [-0.185, +0.115]. Abstention is real, correlated, and mishandled. With four of five detectors silent and the survivor reporting "real", the system returns P(AI) = 0.9985, because an all-NaN input scores 0.9995 in a learner never fitted with missingness. The three AIDE checkpoints fail together, sharing one preprocessing path. A quorum rule requiring two distinct architectures prevents both failures with no retraining. We also find Corpus A carries a class-conditional JPEG bias severe enough to separate the classes from the header alone, which limits every in-domain number we report. Code, harness, hash-identified artifacts and all corrections are released.