Data to 14 Oct 2026

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

arXiv 2412.04292 ↗First posted 5 Dec 2024cs.CV cs.AIcited by 108

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode trust in digital content, resulting in severe repercussions. Despite some progress, academia has not yet created a large and diversified deepfake detection dataset for social media, nor has it devised an effective solution to address this issue. In this paper, we introduce the Social media Image Detection dataSet (SID-Set), which offers three key advantages: (1) extensive volume, featuring 300K AI-generated/tampered and authentic images with comprehensive annotations, (2) broad diversity, encompassing fully synthetic and tampered images across various classes, and (3) elevated realism, with images that are predominantly indistinguishable from genuine ones through mere visual inspection. Furthermore, leveraging the exceptional capabilities of large multimodal models, we propose a new image deepfake detection, localization, and explanation framework, named SIDA (Social media Image Detection, localization, and explanation Assistant). SIDA not only discerns the authenticity of images, but also delineates tampered regions through mask prediction and provides textual explanations of the model's judgment criteria. Compared with state-of-the-art deepfake detection models on SID-Set and other benchmarks, extensive experiments demonstrate that SIDA achieves superior performance among diversified settings. The code, model, and dataset will be released.

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 72 of its 98 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

72 of 98 references.

Closest ancestors · 3

Same direction, newest first

Other references · 69

2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
2023GPT-4 Technical Reportcited by 18,396
2014Microsoft COCO: Common Objects in Contextcited by 17,608
2024The Llama 3 Herd of Modelscited by 14,715
2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
2023Visual Instruction Tuningcited by 7,869
2023Improved Baselines with Visual Instruction Tuningcited by 4,418
2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230

38 more

2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
2022Diffusion Models in Vision: A Surveycited by 1,015
2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
2023Vision-Language Models for Vision Tasks: A Surveycited by 839
2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
2024Large Language Models: A Surveycited by 525
2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 509
2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
2019Unified Vision-Language Pre-Training for Image Captioning and VQAcited by 494
2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 455
2023DIRE for Diffusion-Generated Image Detectioncited by 390
2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 321
2022On the detection of synthetic images generated by diffusion modelscited by 283
2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 265
2023PixelLM: Pixel Reasoning with Large Multimodal Modelcited by 222
2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 173
2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 166
2023GSVA: Generalized Segmentation via Multimodal Large Language Modelscited by 154
2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
2022TruFor: Leveraging all-round clues for trustworthy image forgery detection and localizationcited by 130
2024OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understandingcited by 127
2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 126
2023Transformer-Based Visual Segmentation: A Surveycited by 124
2021MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detectioncited by 117
2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
2023LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Modelscited by 113
2021Representative Forgery Mining for Fake Face Detectioncited by 108
2023Contextual Object Detection with Multimodal Large Language Modelscited by 100
2024LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detectioncited by 89
2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
2023CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Imagescited by 84
2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 76

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 45; 2026: 63.

108 papers.

Sort:

By area:

2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanationcited by 68
2025LEGION: Learning to Ground and Explain for Synthetic Image Detectioncited by 65
2025BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanationcited by 33
2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
2025BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLMcited by 29
2025Toward Generalizable Forgery Detection and Reasoningcited by 20
2025Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approachcited by 17
2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
2025FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensicscited by 11
2025AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbationscited by 8
2025RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detectioncited by 8
2025Semantic Visual Anomaly Detection and Reasoning in AI-Generated Imagescited by 8

38 more

50 most cited of 108 All 108 (JSON)

Similar, not cited

Close in wording, no citation either way