HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
X2-dfd: A framework for explainable and extendable deepfake detection
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 8verdicts
UNVERDICTED 8roles
background 2polarities
background 2representative citing papers
SynthForensics is a people-centric benchmark where face-based detectors lose 13-55 AUC points on modern synthetic videos compared to legacy manipulation sets.
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
PRPO is a paragraph-level policy optimization technique that grounds vision-language model reasoning in image content to raise deepfake detection accuracy and reasoning quality.
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
UniGenDet unifies generative and discriminative models through symbiotic self-attention and detector-guided alignment to co-evolve image generation and authenticity detection.
VRAG-DFD uses RAG to retrieve forgery knowledge and RL-based training to build critical reasoning in MLLMs, delivering state-of-the-art generalization on deepfake detection tasks.
FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.
citing papers explorer
-
HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection
HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
-
SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
SynthForensics is a people-centric benchmark where face-based detectors lose 13-55 AUC points on modern synthetic videos compared to legacy manipulation sets.
-
Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.
-
PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
PRPO is a paragraph-level policy optimization technique that grounds vision-language model reasoning in image content to raise deepfake detection accuracy and reasoning quality.
-
Venus-DeFakerOne: Unified Fake Image Detection & Localization
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
-
UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection
UniGenDet unifies generative and discriminative models through symbiotic self-attention and detector-guided alignment to co-evolve image generation and authenticity detection.
-
VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection
VRAG-DFD uses RAG to retrieve forgery knowledge and RL-based training to build critical reasoning in MLLMs, delivering state-of-the-art generalization on deepfake detection tasks.
-
FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection
FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.