The paper proposes FLAME, a novel framework that detects AI-generated image forgeries by identifying intrinsic energy anomalies caused by the diffusion process, achieving state-of-the-art localization…

The paper introduces SEED, a large-scale benchmark dataset for tracing sequential deepfake facial edits, and proposes FAITH, a frequency-aware Transformer model that effectively detects and orders the…

The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

The paper proposes a unified, architecture-agnostic framework that significantly improves the robustness of deepfake image detectors against adversarial attacks by focusing on higher-order frequency s…

The paper demonstrates that current AI watermark removal techniques fail to achieve true forensic stealth, as the removal process often leaves behind detectable signals that distinguish the output fro…

This paper proposes a 3D CNN detector that leverages temporal artifacts to accurately identify high-quality deepfake videos, demonstrating robust detection even after social media re-encoding.

DeepSignature proposes a novel, cryptographically verifiable watermarking system that uses deep neural networks to embed digital signatures into images, enabling robust source attribution and near 100…

This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generative…

This paper addresses the challenge of detecting and explaining AI-manipulated segments within long, untrimmed videos by proposing a new benchmark and a coarse-to-fine forensic detection framework.

This study comparatively evaluates four CNN architectures (VGG16, ResNet50, EfficientNetB0, and XceptionNet) for fake image detection, finding VGG16 achieved the highest accuracy (91%).

The paper proposes the Shortcut Subspace Suppression (S^3) framework to improve deepfake detection generalization by explicitly identifying and suppressing method-specific shortcuts in learned feature…

The paper proposes a simple, generic attack strategy—re-watermarking—that reliably suppresses existing watermarks, demonstrating that watermarks can be used to attack other watermarks.

The paper introduces TECCI, a novel and challenging benchmark dataset of 7550 image-edit pairs, and demonstrates that current state-of-the-art text-guided image editing models struggle significantly w…

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…

The paper introduces FraudBench, a multimodal benchmark designed to detect AI-generated fraudulent refund evidence, finding that current AI models struggle significantly with claim-conditioned fake-da…

The paper introduces 'contrastive privacy,' a formal, model-agnostic, and quantitative method for evaluating the semantic success of AI-based sanitization across multiple media modalities.

TimeMark proposes a trustworthy time watermarking framework that uses cryptographic techniques and error-correcting codes to achieve 100% accurate recovery of the generation time from AIGC, resisting…

Dual-Guard introduces a dual-channel latent watermarking framework that simultaneously embeds global provenance and localized content anchors into diffusion images, achieving robust detection against…

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper proposes AEGIS, a novel diffusion-guided method for injecting adversarial perturbations into the latent space to create generalizable and robust defenses against advanced facial deepfake man…