Proof pending. Core topic summary fields are still materializing.
Deepfake detection is evolving rapidly in response to the increasing sophistication of generative AI technologies. Recent research emphasizes the importance of leveraging contextual information, audio-visual coherence, and advanced reasoning techniques to enhance detection accuracy. New frameworks, such as Context-based Audio Deepfake Detectors and Holistic Audio-Visual Intrinsic Coherence models, show significant improvements in identifying manipulated content. These advancements are crucial for builders in the field, as they address the growing threats to personal security and societal trust posed by deepfakes. By integrating innovative methodologies, such as self-supervised learning and dynamic curriculum training, the detection systems are becoming more robust and generalizable, ensuring they can adapt to evolving manipulation techniques. This ongoing progress is essential for maintaining digital integrity and protecting users from misinformation.
Topic-specific paper and score movement from the daily diff ledger.
Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. We create and analyze...
The rapid progress of generative AI has enabled hyper-realistic audio-visual deepfakes, intensifying threats to personal security and social trust. Most existing deepfake detectors rely either on uni-...
With the rapid advancement of AIGC technology, developing identification methods to address the security challenges posed by deepfakes has become urgent. Face forgery identification techniques can be ...
While spatiotemporal deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks. These models tend to overfit on fragile temporal spectrum cues, rather than le...
Multimodal large language models (MLLMs) offer a promising path toward interpretable deepfake detection by generating textual explanations. However, the reasoning process of current MLLM-based methods...
This paper describes a submission to the Environment-Aware Speech and Sound Deepfake Detection Challenge (ESDD2) 2026, which addresses component-level deepfake detection using the CompSpoofV2 dataset,...
With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely on cross-modal inco...
Partial deepfake speech detection requires identifying manipulated regions that may occur within short temporal portions of an otherwise bona fide utterance, making the task particularly challenging f...
Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forge...
Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel...
Freshness
Canonical route: /topics
Agent Handoff
Canonical ID deepfake-detection | Route /topic/deepfake-detection
REST example
curl https://sciencetostartup.com/api/v1/agent-handoff/topic/deepfake-detectionMCP example
{
"tool": "search_papers",
"arguments": {
"query": "Deepfake Detection",
"cluster": "Deepfake Detection"
}
}source_context
{
"surface": "topic",
"mode": "topic",
"query": "Deepfake Detection",
"normalized_query": "deepfake-detection",
"route": "/topic/deepfake-detection",
"paper_ref": null,
"topic_slug": "deepfake-detection",
"benchmark_ref": null,
"dataset_ref": null
}Use This Via API or MCP
Topic pages bundle paper counts, viability trends, author concentration, and top questions into one canonical surface your agents can reference before they open Signal Canvas or create a workspace.