This work formats the AI-generated image detection task as a Visual Question Answering problem, leveraging a fine-tuned vision-language framework to fully exploit the complementary information between visual and textual modalities, and proposes a novel high-resolution AI-generated image detector, termed LHSDet.
Abstract
Driven by advances in diffusion models and autoregressive models, the fidelity and resolution of AI-generated images now rival those of real images. However, existing AI-generated image detection methods often downsample the images, inevitably overlooking critical low-level texture details in high-resolution AI-generated images, therefore limiting their detection performance. In addition, the ceaseless emergence of unknown generative models makes large-scale pre-training datasets inaccessible. To address these challenges, we propose a novel high-resolution AI-generated image detector, termed LHSDet. Specifically, we formulate the AI-generated image detection task as a Visual Question Answering problem, leveraging a fine-tuned vision-language framework to fully exploit the complementary information between visual and textual modalities. Recognizing that the default visual encoder of existing vision-language models is not tailored for AI-generated image detection, we redesign a visual encoder to better capture both the low-level and high-level artifacts inherent in AI-generated images. Furthermore, we incorporate a semantic-level textual branch to enable multi-modal feature fusion and detection. Consequently, LHSDet employs a triple-branch architecture to extract complementary multi-modal features: a low-level visual branch that aggregates non-overlapping patches for local texture cues, a high-level visual branch based on SigLIP2 for global perception feature extraction, and a semantic-level textual branch that generates captions using BLIP-2. Extensive experimental results demonstrate that LHSDet achieves high detection accuracy and robust performance across diverse generative models, including both diffusion and autoregressive models.
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
This work establishes a new paradigm for generated image detection by recasting the detection task as a problem of machine unlearning, and introduces two detection methods: data-free detection, which prunes model parameters to induce unlearning without data access, and data-driven detection, which optimizes LVMs to unlearn knowledge tied to generated images.
Jun Nie, Yonggang Zhang, Tongliang Liu et al.· 0 citations
Vision-Language Large Models (VLLMs) are promising for AI-generated image (AIGI) detection because they can produce both a prediction and a natural-language output. However, most existing VLLM-based detectors primarily fine-tune the language side while giving limited attention to low-level visual forensic cues. They also often depend on manually crafted prompts or human-annotated rationales, which limits scalability.We present UC-VLM, a unified multi-stage framework for AIGI detection that relies solely on binary supervision. UC-VLM first identifies effective instruction variants automatically. It then reuses the same binary label within a multi-stage training framework: (i) a visual discrimination objective that strengthens sensitivity to non-semantic forensic cues, and (ii) a label-conditioned generation objective that uses the binary label to supervise textual outputs. This design turns weak binary supervision into a shared supervision signal for both the visual pathway and the language output. Our key novelty is a unified multi-stage binary-supervised framework that consistently reuses the same authenticity labels for visual adaptation and label-conditioned text generation, while leveraging automatically optimized instructions to reduce prompt sensitivity without requiring human-written rationales or hand-crafted prompts.Experiments show that UC-VLM achieves 96.1% average accuracy on GenImage, exceeding the strongest prior result by 4.6%, and obtains 69.6% / 77.9% accuracy on Chameleon under ProGAN / SDV1.4 training, surpassing the best baseline by 11.2% / 15.3%, respectively.
Lei Tan, Shuwei Li, Mohan S. Kankanhalli et al.· 0 citations
Deep learning-based generative models have made a major leap forward in the world of image generation with the help
of Artificial Intelligence. One of the most notable of these developments is text-to-image synthesis, which can
automatically generate images based on natural language descriptions. In this work, an AI-based image generation system
is introduced that utilizes a Stable Diffusion model fine-tuned with Low-Rank Adaptation (LoRA) for domain-specific
image generation. The main idea of the proposed system is to combine the text encoding of CLIP, the latent compression
of Variational Autoencoder (VAE), and the denoising ability of diffusion to create images that are both semantically
relevant and visually coherent based on text prompts. The proposed approach was tested on a Pokemon image-caption
dataset for fine-tuning the pre-trained Stable Diffusion model and its effectiveness evaluated. The study shows that the
diffusion-based architectures outperform the traditional GAN based methods in terms of image quality, training stability,
semantic alignment, and output diversity. The main advantage of LoRA fine-tuning was the substantial decrease in
computational load, which involved updating just a small fraction of trainable parameters without compromising the
model's performance. Experimental results indicated that successful images of Pokemon could be generated, and that the
images were consistent with the text attributes such as color, type, and appearance. The results demonstrate that SD+LoRA
is an efficient and scalable domain-specific text-to-image generation system. The research underscores the rising
significance of diffusion-based generative AI in digital content creation, imaginative design, entertainment, and cleverness
in visual generation systems
Ankam Pavitra, R. Mallikharjun, Dr. L Jagadeesh Naik· International Journal of Dru...· 0 citations
PPM-CLIP is proposed, a new framework that shifts from static classification to conditional generative modeling based on the CLIP vision-language model, and a Probabilistic Prompt Modeling module is used as a generator that produces an adaptive distribution of prompts according to the input image.
Xinyu Wang, Yingxin Lai, Zhiming Luo et al.· 0 citations
Detection and localization of AI-tampered images are critical for trustworthy AI, yet modern generative models have made such manipulations increasingly difficult to identify. While traditional binary classifiers can detect image tampering, they lack interpretability and generalization. Vision-Language Models (VLMs) offer a promising alternative due to their strong visual understanding and reasoning capabilities; however, existing approaches typically rely on supervised finetuning with curated explanations rather than exploiting their inherent reasoning capabilities. In this work, we investigate whether VLMs can be trained to reason about AI-generated image edits using reinforcement learning (RL) rather than explicit reasoning supervision. Motivated by the success in Group Relative Policy Optimization (GRPO), an RL technique that incentivizes the model to reason by generating thinking traces prior to giving the final answer, we propose a GRPO-based training framework that utilizes simple accuracy and format rewards. Given an input image, the model produces a structured reasoning trace and predicts whether the image has been tampered with. A lightweight segmentation model is then guided by the reasoning output to generate pixel-level localization masks. Experiments across multiple image manipulation datasets demonstrate that our approach achieves competitive detection and localization performance compared to state-of-the-art image forgery detectors, despite requiring substantially weaker supervision. We introduce effective intersection over union (eff-IoU), a unified metric to jointly evaluate detection and localization. These results suggest that reinforcement learning provides an effective and scalable mechanism for teaching VLMs to reason about AI-generated content.
Darsha Udayanga, Pin-Yu Chen, Payel Das et al.· 0 citations