Além do Desempenho: Um Estudo da Confiabilidade de Detectores de Deepfakes

Deepfakes are synthetic media generated by artificial intelligence, with positive applications in education and creativity, but also serious negative impacts such as fraud, misinformation, and privacy violations. Although detection techniques have advanced, comprehensive evaluation methods that go beyond classification performance remain lacking. This paper proposes a reliability assessment framework based on four pillars: transferability, robustness, interpretability, and computational efficiency. An analysis of five state-of-the-art methods revealed significant progress as well as critical limitations.

Lightweight Resolution-Aware Audio Deepfake Detection via Cross-Scale Attention and Consistency Learning

Audio deepfake detection has become increasingly challenging due to rapid advances in speech synthesis and voice conversion technologies, particularly under channel distortions, replay attacks, and real-world recording conditions. This paper proposes a resolution-aware audio deepfake detection framework that explicitly models and aligns multi-resolution spectral representations through cross-scale attention and consistency learning. Unlike conventional single-resolution or implicit feature-fusion approaches, the proposed method enforces agreement across complementary time--frequency scales. The proposed framework is evaluated on three representative benchmarks: ASVspoof 2019 (LA and PA), the Fake-or-Real (FoR) dataset, and the In-the-Wild Audio Deepfake dataset under a speaker-disjoint protocol. The method achieves near-perfect performance on ASVspoof LA (EER 0.16%), strong robustness on ASVspoof PA (EER 5.09%), FoR rerecorded audio (EER 4.54%), and in-the-wild deepfakes (AUC 0.98, EER 4.81%), significantly outperforming single-resolution and non-attention baselines under challenging conditions. The proposed model remains lightweight and efficient, requiring only 159k parameters and less than 1~GFLOP per inference, making it suitable for practical deployment. Comprehensive ablation studies confirm the critical contributions of cross-scale attention and consistency learning, while gradient-based interpretability analysis reveals that the model learns resolution-consistent and semantically meaningful spectral cues across diverse spoofing conditions. These results demonstrate that explicit cross-resolution modeling provides a principled, robust, and scalable foundation for next-generation audio deepfake detection systems.

Phase4DFD: Multi-Domain Phase-Aware Attention for Deepfake Detection

Recent deepfake detection methods have increasingly explored frequency domain representations to reveal manipulation artifacts that are difficult to detect in the spatial domain. However, most existing approaches rely primarily on spectral magnitude, implicitly under exploring the role of phase information. In this work, we propose Phase4DFD, a phase aware frequency domain deepfake detection framework that explicitly models phase magnitude interactions via a learnable attention mechanism. Our approach augments standard RGB input with Fast Fourier Transform (FFT) magnitude and local binary pattern (LBP) representations to expose subtle synthesis artifacts that remain indistinguishable under spatial analysis alone. Crucially, we introduce an input level phase aware attention module that uses phase discontinuities commonly introduced by synthetic generation to guide the model toward frequency patterns that are most indicative of manipulation before backbone feature extraction. The attended multi domain representation is processed by an efficient BNext M backbone, with optional channel spatial attention applied for semantic feature refinement. Extensive experiments on the CIFAKE and DFFD datasets demonstrate that our proposed model Phase4DFD outperforms state of the art spatial and frequency-based detectors while maintaining low computational overhead. Comprehensive ablation studies further confirm that explicit phase modeling provides complementary and non-redundant information beyond magnitude-only frequency representations.

Deepfake detectors are DUMB: A benchmark to assess adversarial training robustness under transferability constraints

Deepfake detection systems deployed in real-world environments are subject to adversaries capable of crafting imperceptible perturbations that degrade model performance. While adversarial training is a widely adopted defense, its effectiveness under realistic conditions -- where attackers operate with limited knowledge and mismatched data distributions - remains underexplored. In this work, we extend the DUMB -- Dataset soUrces, Model architecture and Balance - and DUMBer methodology to deepfake detection. We evaluate detectors robustness against adversarial attacks under transferability constraints and cross-dataset configuration to extract real-world insights. Our study spans five state-of-the-art detectors (RECCE, SRM, XCeption, UCF, SPSL), three attacks (PGD, FGSM, FPBA), and two datasets (FaceForensics++ and Celeb-DF-V2). We analyze both attacker and defender perspectives mapping results to mismatch scenarios. Experiments show that adversarial training strategies reinforce robustness in the in-distribution cases but can also degrade it under cross-dataset configuration depending on the strategy adopted. These findings highlight the need for case-aware defense strategies in real-world applications exposed to adversarial attacks.

Agentic AI Microservice Framework for Deepfake and Document Fraud Detection in KYC Pipelines

The rapid proliferation of synthetic media, presentation attacks, and document forgeries has created significant vulnerabilities in Know Your Customer (KYC) workflows across financial services, telecommunications, and digital-identity ecosystems. Traditional monolithic KYC systems lack the scalability and agility required to counter adaptive fraud. This paper proposes an Agentic AI Microservice Framework that integrates modular vision models, liveness assessment, deepfake detection, OCR-based document forensics, multimodal identity linking, and a policy driven risk engine. The system leverages autonomous micro-agents for task decomposition, pipeline orchestration, dynamic retries, and human-in-the-loop escalation. Experimental evaluations demonstrate improved detection accuracy, reduced latency, and enhanced resilience against adversarial inputs. The framework offers a scalable blueprint for regulated industries seeking robust, real-time, and privacy-preserving KYC verification.

Analyzing Reasoning Shifts in Audio Deepfake Detection under Adversarial Attacks: The Reasoning Tax versus Shield Bifurcation

Audio Language Models (ALMs) offer a promising shift towards explainable audio deepfake detections (ADDs), moving beyond \textit{black-box} classifiers by providing some level of transparency into their predictions via reasoning traces. This necessitates a new class of model robustness analysis: robustness of the predictive reasoning under adversarial attacks, which goes beyond existing paradigm that mainly focuses on the shifts of the final predictions (e.g., fake v.s. real). To analyze such reasoning shifts, we introduce a forensic auditing framework to evaluate the robustness of ALMs' reasoning under adversarial attacks in three inter-connected dimensions: acoustic perception, cognitive coherence, and cognitive dissonance. Our systematic analysis reveals that explicit reasoning does not universally enhance robustness. Instead, we observe a bifurcation: for models exhibiting robust acoustic perception, reasoning acts as a defensive \textit{``shield''}, protecting them from adversarial attacks. However, for others, it imposes a performance \textit{``tax''}, particularly under linguistic attacks which reduce cognitive coherence and increase attack success rate. Crucially, even when classification fails, high cognitive dissonance can serve as a \textit{silent alarm}, flagging potential manipulation. Overall, this work provides a critical evaluation of the role of reasoning in forensic audio deepfake analysis and its vulnerabilities.

ASVspoof 5: Evaluation of Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech

ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake detection solutions. A significant change from previous challenge editions is a new crowdsourced database collected from a substantially greater number of speakers under diverse recording conditions, and a mix of cutting-edge and legacy generative speech technology. With the new database described elsewhere, we provide in this paper an overview of the ASVspoof 5 challenge results for the submissions of 53 participating teams. While many solutions perform well, performance degrades under adversarial attacks and the application of neural encoding/compression schemes. Together with a review of post-challenge results, we also report a study of calibration in addition to other principal challenges and outline a road-map for the future of ASVspoof.

A Novel Unified Approach to Deepfake Detection

The advancements in the field of AI is increasingly giving rise to various threats. One of the most prominent of them is the synthesis and misuse of Deepfakes. To sustain trust in this digital age, detection and tagging of deepfakes is very necessary. In this paper, a novel architecture for Deepfake detection in images and videos is presented. The architecture uses cross attention between spatial and frequency domain features along with a blood detection module to classify an image as real or fake. This paper aims to develop a unified architecture and provide insights into each step. Though this approach we achieve results better than SOTA, specifically 99.80%, 99.88% AUC on FF++ and Celeb-DF upon using Swin Transformer and BERT and 99.55, 99.38 while using EfficientNet-B4 and BERT. The approach also generalizes very well achieving great cross dataset results as well.

XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection

Advanced speech synthesis technologies have enabled highly realistic speech generation, posing security risks that motivate research into audio deepfake detection (ADD). While state space models (SSMs) offer linear complexity, pure causal SSMs architectures often struggle with the content-based retrieval required to capture global frequency-domain artifacts. To address this, we explore the scaling properties of hybrid architectures by proposing XLSR-MamBo, a modular framework integrating an XLSR front-end with synergistic Mamba-Attention backbones. We systematically evaluate four topological designs using advanced SSM variants, Mamba, Mamba2, Hydra, and Gated DeltaNet. Experimental results demonstrate that the MamBo-3-Hydra-N3 configuration achieves competitive performance compared to other state-of-the-art systems on the ASVspoof 2021 LA, DF, and In-the-Wild benchmarks. This performance benefits from Hydra's native bidirectional modeling, which captures holistic temporal dependencies more efficiently than the heuristic dual-branch strategies employed in prior works. Furthermore, evaluations on the DFADD dataset demonstrate robust generalization to unseen diffusion- and flow-matching-based synthesis methods. Crucially, our analysis reveals that scaling backbone depth effectively mitigates the performance variance and instability observed in shallower models. These results demonstrate the hybrid framework's ability to capture artifacts in spoofed speech signals, providing an effective method for ADD.

On the Holistic Approach for Detecting Human Image Forgery

The rapid advancement of AI-generated content (AIGC) has escalated the threat of deepfakes, from facial manipulations to the synthesis of entire photorealistic human bodies. However, existing detection methods remain fragmented, specializing either in facial-region forgeries or full-body synthetic images, and consequently fail to generalize across the full spectrum of human image manipulations. We introduce HuForDet, a holistic framework for human image forgery detection, which features a dual-branch architecture comprising: (1) a face forgery detection branch that employs heterogeneous experts operating in both RGB and frequency domains, including an adaptive Laplacian-of-Gaussian (LoG) module designed to capture artifacts ranging from fine-grained blending boundaries to coarse-scale texture irregularities; and (2) a contextualized forgery detection branch that leverages a Multi-Modal Large Language Model (MLLM) to analyze full-body semantic consistency, enhanced with a confidence estimation mechanism that dynamically weights its contribution during feature fusion. We curate a human image forgery (HuFor) dataset that unifies existing face forgery data with a new corpus of full-body synthetic humans. Extensive experiments show that our HuForDet achieves state-of-the-art forgery detection performance and superior robustness across diverse human image forgeries.