ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection

• URL: http://arxiv.org/abs/2604.16749v1
• Date: Fri, 17 Apr 2026 23:44:33 GMT
• Title: ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection
• Abstract summary: We introduce a novel textbfIn-textbfContext textbfLearning paradigm with comparison-guidance for textbfAudio textbfDeepfake detection.<n>The framework enables the use of audio language models (ALMs) for training-free generalization to unseen deepfakes.
• Score: 7.887913982488066
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio deepfakes pose a significant security threat, yet current state-of-the-art (SOTA) detection systems do not generalize well to realistic in-the-wild deepfakes. We introduce a novel \textbf{I}n-\textbf{C}ontext \textbf{L}earning paradigm with comparison-guidance for \textbf{A}udio \textbf{D}eepfake detection (\textbf{ICLAD}). The framework enables the use of audio language models (ALMs) for training-free generalization to unseen deepfakes and provides textual rationales on the detection outcome. At the core of ICLAD is a pairwise comparative reasoning strategy that guides the ALM to discover and filter hallucinations and deepfake-irrelevant acoustic attributes. The ALM works alongside a specialized deepfake detector, whereby a routing mechanism feeds out-of-distribution samples to the ALM. On in-the-wild datasets, ICLAD improves macro F1 over the specialized detector, with up to $2\times$ relative improvement. Further analysis demonstrates the flexibility of ICLAD and its potential for deployment on recent open-source ALMs.

Related papers

• The Regularizing Power of Language-Training Deepfake Detectors [57.529452351298495]
  Deepfake detection generally suffers from overfitting to low-level domain-specific artifacts.<n>We use a dual-encoder architecture, pairing a frozen specialist detector with a LoRA-tuned MLLM encoder.<n>We employ a reinforcement learning stage that encourages the model to generate descriptive reasoning before classifying.
  arXiv  Detail & Related papers  (2026-05-29T12:01:17Z)
• Reasoning-Aware AIGC Detection via Alignment and Reinforcement [55.09684020007737]
  REVEAL is a framework that generates interpretable reasoning chains before classification.<n>It achieves state-of-the-art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-04-21T07:29:55Z)
• SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment [74.05278327933006]
  We propose SAVe, a self-supervised audio-visual deepfake detection framework that learns entirely on authentic videos.<n>SAVE generates on-the-fly, identity-preserving, region-aware self-blended pseudo-manipulations to emulate tampering artifacts.<n>To capture cross-modal evidence, SAVe also models lip-speech synchronization.
  arXiv  Detail & Related papers  (2026-03-26T08:01:35Z)
• Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection [27.756028843178708]
  generative AI has enabled hyper-realistic audio-visual deepfakes, intensifying threats to personal security and social trust.<n>Most existing deepfake detectors rely on uni-modal artifacts or audio-visual discrepancies, failing to jointly leverage both sources of information.<n>We argue that robust and generalizable detection should be grounded in intrinsic audio-visual coherence within and across modalities.<n>We introduce HiFi-AVDF, a high-fidelity audio-visual deepfake dataset featuring both text-to-video and image-to-video forgeries from state-of-the-art commercial generators.
  arXiv  Detail & Related papers  (2026-03-25T05:44:25Z)
• Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection [6.491407316650203]
  Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have shown strong generalisation in detecting image and video deepfakes.<n>We aim to explore the potential of MLLMs for audio deepfake detection.
  arXiv  Detail & Related papers  (2026-01-02T18:17:22Z)
• KLASSify to Verify: Audio-Visual Deepfake Detection Using SSL-based Audio and Handcrafted Visual Features [1.488627850405606]
  We propose multimodal approaches for the AV-Deepfake1M 2025 challenge.<n>For the visual modality, we leverage handcrafted features to improve interpretability and adaptability.<n>For the audio modality, we adapt a self-supervised learning backbone coupled with graph attention networks to capture rich audio representations.<n>Our approach strikes a balance between performance and real-world deployment, focusing on resilience and potential interpretability.
  arXiv  Detail & Related papers  (2025-08-10T13:29:08Z)
• Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection [11.497620257835964]
  We propose CCKT-Det trained without any extra supervision.<n>The proposed framework constructs a cyclic and dynamic knowledge transfer from language queries and visual region features extracted from vision-language models (VLMs)<n> CCKT-Det can consistently improve performance as the scale of VLMs increases, all while requiring the detector at a moderate level of overhead.
  arXiv  Detail & Related papers  (2025-03-14T02:04:28Z)
• DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization [13.840950434728533]
  DiMoDif is an audio-visual deepfake detection framework.<n>It exploits the inter-modality differences in machine perception of speech.<n>It temporally localizes the deepfake forgery.
  arXiv  Detail & Related papers  (2024-11-15T13:47:33Z)
• X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection [55.77552681618732]
  X2-DFD is an eXplainable and eXtendable framework based on multimodal large-language models (MLLMs) for deepfake detection.<n>The first stage, Model Feature Assessment, systematically evaluates the detectability of forgery-related features for the MLLM.<n>The second stage, Explainable dataset Construction, consists of two key modules: Strong Feature Strengthening and Weak Feature Supplementing.<n>The third stage, Fine-tuning and Inference, involves fine-tuning the MLLM on the constructed dataset and deploying it for final detection and explanation.
  arXiv  Detail & Related papers  (2024-10-08T15:28:33Z)
• OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer [63.141027246418]
  We propose Open-Vocabulary Light-Weighted Detection Transformer (OVLW-DETR), a deployment friendly open-vocabulary detector with strong performance and low latency. We provide an end-to-end training recipe that transferring knowledge from vision-language model (VLM) to object detector with simple alignment. Experimental results demonstrate that the proposed approach is superior over existing real-time open-vocabulary detectors on standard Zero-Shot LVIS benchmark.
  arXiv  Detail & Related papers  (2024-07-15T12:15:27Z)
• Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization [63.66349334291372]
  We propose a framework with Meta prompt and Instance Contrastive learning (MIC) schemes. Firstly, we simulate a novel-class-emerging scenario to help the prompt that learns class and background prompts generalize to novel classes. Secondly, we design an instance-level contrastive strategy to promote intra-class compactness and inter-class separation, which benefits generalization of the detector to novel class objects.
  arXiv  Detail & Related papers  (2024-03-14T14:25:10Z)
• NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake Detection [50.33525966541906]
  Existing multimodal detection methods capture audio-visual inconsistencies to expose Deepfake videos. We propose a novel Deepfake detection method to mine the correlation between Non-critical Phonemes and Visemes, termed NPVForensics. Our model can be easily adapted to the downstream Deepfake datasets with fine-tuning.
  arXiv  Detail & Related papers  (2023-06-12T06:06:05Z)
• F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models [54.21757555804668]
  We present F-VLM, a simple open-vocabulary object detection method built upon Frozen Vision and Language Models. F-VLM simplifies the current multi-stage training pipeline by eliminating the need for knowledge distillation or detection-tailored pretraining.
  arXiv  Detail & Related papers  (2022-09-30T17:59:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.