GurAI is proposed, a transparent logistic late-fusion method that combines Rich384 and DeMamba logits that suggests that transparent late fusion can exploit complementary detector strengths more effectively than architectural redesign alone when facing generator diversity.
Abstract
The proliferation of text-to-video generative models—including commercial systems such as Sora, Veo, Runway Gen-3, and Kling—makes automated detection of AI-generated videos an urgent problem in multimedia forensics. We present a study with two interleaved contributions: a cross-family benchmark and two improvements to the detection pipeline. For the benchmark, we evaluate three methodologically distinct detector families on three public datasets (VidProM, DeepAction, and DeCoF_T2V), spanning diverse open-source and commercial generators: ReStraV, a geometry-supervised detector grounded in the perceptual straightening hypothesis; D3, a training-free detector based on second-order XCLIP temporal statistics; and DeMamba, a supervised Bidirectional Mamba module on frozen XCLIP features. ReStraV and DeMamba achieve broadly comparable global performance on large datasets (VidProM AUC 0.985/0.989; DeCoF_T2V AUC 0.990/0.992), while D3 remains weak as a stand-alone detector under a fixed detection threshold calibrated on VidProM and transferred unchanged to the other benchmarks (AUC 0.534/0.410/0.454 on VidProM/DeepAction/DeCoF_T2V). Per-generator analysis reveals complementary failure modes: DeMamba recovers several hard commercial generators where ReStraV struggles, whereas ReStraV remains competitive in low-data settings at substantially lower computational cost. To bridge these weaknesses, we propose two improvements. First, Rich384 enriches ReStraV’s compact geometric descriptor with DINOv2 temporal embeddings, strengthening ranking quality on large benchmarks and recovering generators that geometry alone misses (AUC 0.995 on VidProM and 0.998 on DeCoF_T2V, with DeepAction AUC decreasing to 0.805). Second, we propose GurAI, our transparent logistic late-fusion method that combines Rich384 and DeMamba logits, raising threshold-free AUC to 0.998/0.999 on VidProM and DeCoF_T2V while preserving interpretability. On the small DeepAction cohort, fusion improves selected per-generator fake recalls at the cost of elevated REAL false positives (AUC 0.769; REAL accuracy 0.460).Our analysis suggests that transparent late fusion can exploit complementary detector strengths more effectively than architectural redesign alone when facing generator diversity.
A data-generation pipeline that captions real photographs with a vision–language model and regenerates them with modern text-to-image systems, producing semantically aligned real/synthetic pairs that isolate generative artifacts from image content is described.
The rapid advancement of generative AI has outpaced our ability to reliably detect its outputs, particularly when detectors encounter generators they have not seen before. We introduce GenSyn10, a CIFAR-10-aligned synthetic image dataset of 60,000 images (10 classes, 32$\times$32, 50k/10k split) generated using three architecturally diverse state-of-the-art models: FLUX.2-dev (Rectified Flow Transformer), HunyuanImage-3.0 (MoE Transformer), and Qwen-Image-2512 (Multimodal Diffusion Transformer), to advance research in AI-generated image detection. A central challenge in this domain is that detectors perform well on known generators but degrade on unseen ones. GenSyn10 addresses this limitation by curating data from multiple contemporary architectures under a standardized generation protocol, enabling controlled and systematic evaluation of out-of-distribution (OOD) generalization to novel generators. Images are generated using a template-based prompt engine and downsampled to ensure consistency. We evaluate 17 image classification models under a four-stage protocol: real-data baseline, zero-shot transfer, fine-tuning, and retention. Despite a measurable domain gap, CIFAR-10-trained models achieve up to 96.86\% zero-shot accuracy on GenSyn10, increasing to 99.88\% after fine-tuning. In binary real-vs-synthetic classification, fine-tuned models achieve 97-99.9\% accuracy on seen generators but drop to 79-96\% on images from an unseen generator, highlighting persistent limitations in OOD generalization. These results establish GenSyn10 as a controlled benchmark for studying synthetic image detection beyond single-generator settings, supporting research on robustness, domain adaptation, and cross-generator generalization.
Md Faraz Kabir Khan, Saeed Anwar, G. Hassan· 0 citations
Deepfake image detection is served by three fundamentally different paradigms - commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors - that are rarely evaluated under a common protocol, making direct comparison difficult. We introduce VendorBench-100, a cross-paradigm benchmark that evaluates 36 representative models using a single adversarial 100-image corpus, a unified output schema, and a common evaluation framework. Models are ranked primarily by the Matthews correlation coefficient (MCC), with ROC-AUC reported as a threshold-independent measure of ranking ability. Rather than maximizing size, it emphasizes real-world difficulty through a taxonomy of eight edge-case families such as face swaps, text-to-video stills, AI photo edits, avatar compositing, opaque-provenance images, and compressed research frames. Commercial APIs achieve the strongest median performance, followed by vision LLMs and open-source detectors, though individual open-source models remain competitive with the best LLMs. Across all 36 models, MCC and ROC-AUC are strongly correlated (Pearson r ~ 0.86); the more consequential finding is narrower and one-directional: a subset of otherwise strong rankers are miscalibrated at their shipped default threshold, so a high ROC-AUC can overstate real-world deployability. Separately, raw accuracy and F1 are unreliable on this corpus's imbalanced class split, since a model that predicts"fake"indiscriminately scores deceptively well on both while offering no real discriminative skill. No single metric is safe in isolation: MCC and specificity should always accompany ROC-AUC and accuracy. We release the complete evaluation framework and results. Code and data: https://github.com/sharayu-20/vendorbench-100
S. N. Deshmukh, Md. Rashidunnabi, Nelton Tiago Gemo et al.· 0 citations
The advent of generative AI models that can generate some of the most realistic images including DALL·E, Midjourney, and Stable Diffusion has posed a significant threat to digital forensics and media authenticity verifications. Conventional methods of forgery detection, which focus on splicing or copy-move manipulations, are not very efficient in the case of AI-generated images, which do not contain any explicit tampering traces. This paper presents Attention-Based Deep Learning Pipeline of AI-Created Image Recognition, intended to resolve the increasing challenge of separating AI-synthesized and authentic imagery. The proposed architecture incorporates three integrated branches, including low-level statistical feature extraction, high-level semantic representation learning, and attention-based feature refinement mechanism. The features that are extracted are combined and fed through a fully connected classifier to generate final predictions. The Synthbuster dataset that consists of images of several generative models, including DALL·E 2, DALL·E 3, Firefly, Glide, and versions of Stable Diffusion, were experimentally evaluated. The suggested framework score had an average AUC of 97.4%, as well as high accuracy, precision, recall, and F1-score. These findings support the robustness and generalization ability of the proposed model in detecting AI-generated images in a variety of generators and conditions.
Nadia Ali· Al-Noor Journal of Engineeri...· 0 citations
Deepfake detectors that achieve near-perfect scores on academic benchmarks collapse on real-world content: recent in-the-wild evaluations report AUC drops of 45-50% for state-of-the-art open-source models. We argue this gap is structural: static detectors are trained once against a moving generative frontier. We present BitMind Forensics (BMF), trained through Bittensor SN34, an open adversarial competition that continually refreshes the training distribution. We evaluate one dated export comprising image, general-video, and human-video checkpoints across nineteen public datasets: the canonical face-swap suites (FaceForensics++, Celeb-DF v1/v2/++, DFDC, DFD, UADFV, DF40) and recent in-the-wild and AI-generated-media benchmarks (Sumsub, Deepfake-Eval-2024, WildRF, Community Forensics, AIGCDetectBench, GenImage, AI-GenBench, AIGIBench, RAID, GenVidBench, GenVideo-100K). BMF reaches 0.936 AUC on Sumsub's original images and 0.872 pooled AUC over its full four-condition manipulation battery (1.4M images), staying robust under perturbation (0.855 JPEG, 0.799 downscaled), while GPEN enhancement improves detection (0.996). On Deepfake-Eval-2024, it matches the best commercial detector on images (0.915 vs 0.90) and exceeds it on video (0.822 vs 0.79), far above the best open-source detectors (0.56 and 0.63). It reaches 0.991 AUC on a 21-generator AI-image panel and 0.918 on GenVidBench, and exceeds the FF++-trained frontier on DFDC (0.947 vs 0.843) and Celeb-DF v2 (0.9985 vs 0.956), both contamination-audited, with statistical parity on Celeb-DF++. In a temporal study, successive dated exports improve on held-out media from generators absent from the static baseline's training (image 0.842 to 0.902; video 0.864 to 0.936). Our evaluation harness is public, and at publication the production API serves the exact evaluated snapshot for independent verification.