Search Results (40)

Deepfakes threaten sensor-based authentication systems, including biometric sensors, surveillance cameras, and IoT edge devices. Unimodal detectors remain vulnerable to modality-specific attacks. We propose a multimodal deepfake detection framework optimized for resource-constrained edge devices, featuring a novel cross-modal attention fusion mechanism with adaptive gating. The architecture combines enhanced Res2Net for audio, temporal 3D CNN with SE attention for video, and bidirectional cross-modal attention with quality-based gates. On our benchmark (5472 audio + 1842 video samples), the fusion model achieves 96.7% accuracy, 96.6% F1-score, 0.988 AUC-ROC, and 3.3% EER. Adversarial testing shows 92.3% accuracy under the Fast Gradient Sign Method (FGSM) attack. The model has a 30.3 MB footprint and runs at 20 FPS on edge hardware. Modality contribution analysis reveals adaptive weighting (72% audio for TTS forgery, 78% video for lip-synced attacks). Cross-dataset evaluation on FakeAVCeleb achieves 92.3% overall accuracy, confirming generalization. Full article

Deepfake detection has become an essential task for ensuring the authenticity and security of digital media. Although recent approaches have achieved notable progress, most existing detectors still exhibit limited generalization to unseen forgery techniques and remain vulnerable to common perturbations such as compression, noise, and adversarial attacks. To overcome these issues, we propose Weakly Supervised EfficientNet Augmented Face Forgery Detector (WAFF), a novel framework that integrates fine-grained per-frame analysis with adaptive video-level fusion. Specifically, WAFF integrates WSEffiNet, an EfficientNet-B3-based backbone enhanced with a Weakly Supervised Data Augmentation Network (WS-DAN). This design generates attention maps to emphasize subtle facial forgery artifacts while encouraging complementary local–global feature learning. At the video level, WAFF incorporates a multi-strategy fusion scheme that combines fake-frame counting, confidence averaging, and attention-guided voting to strike a balance between sensitivity and stability. Extensive experiments on FaceForensics++, Celeb-DF v2, DFD, DFDC, and FFIW-10K demonstrate that WAFF can achieve state-of-the-art performance under both high- and low-quality compression, while also enhancing cross-dataset generalization. Full article

Deepfakes and adjacent synthetic-media capabilities have become a systemic challenge for information integrity, security, and digital trust. Countermeasures now span passive detection methods that infer manipulation from content traces, active provenance systems that cryptographically bind metadata to media, and watermarking approaches that embed detectable signals into content or generative processes. This review presents a rigorous synthesis of tools and technologies to combat deepfakes across modalities (image, video, audio, and selected multimodal settings), drawing primarily from the peer-reviewed literature, standardized benchmarks, and official technical specifications and reports. The review analyzes detection methods, provenance and authentication technologies, with emphasis on cryptographic manifests and threat models, watermarking and content provenance, including diffusion-era watermarking and industrial deployments, adversarial robustness and attacker adaptation, datasets and benchmarks, evaluation metrics across tasks, and deployment and scalability constraints. A dedicated section addresses legal, ethical, and policy issues, focusing on emerging transparency obligations and platform governance. The review finds that no single countermeasure is sufficient in realistic adversarial settings. The strongest practical approach is a layered defense that combines provenance, watermarking, content-based detection, and human oversight. The study concludes with limitations of the current evidence base and prioritized research directions to improve generalization, interoperability, and trustworthy user experiences. Full article

Deepfake technology can produce highly realistic manipulated media which pose as significant cybersecurity threats, including fraud, misinformation, and privacy violations. This research proposes a deepfake prevention approach based on symmetric and asymmetric ciphers. Post-quantum asymmetric ciphers were utilized to perform digital signature operations, which offer essential security services, including integrity, authentication, and non-repudiation. Symmetric ciphers were also employed to provide confidentiality and authentication. Unlike classical ciphers that are vulnerable to quantum attacks, this study adopts quantum-resilient ciphers to offer long-term security. The proposed approach enables entities to digitally sign media content before public release on other platforms. End users can subsequently verify the authenticity of content using the public keys of the media creators. To identify the most efficient ciphers to perform cryptography operations required for deepfake prevention, the study explores the implementation of quantum-resilient symmetric and asymmetric ciphers standardized by NIST, including Dilithium, Falcon, SPHINCS+, and Ascon-80pq. Additionally, this research provides comprehensive comparisons between the various classical and post-quantum ciphers in both categories: symmetric and asymmetric. Experimental results revealed that Dilithium-5 and Falcon-512 algorithms outperform other post-quantum ciphers, with a time delay of 2.50 and 251 ms, respectively, for digital signature operations. The Falcon-512 algorithm also demonstrates superior resource efficiency, making it a cost-effective choice for digital signature operations. With respect to symmetric ciphers, Ascon-80pq achieved the lowest time consumption, taking just 0.015 ms to perform encryption and decryption operations. Also, it is a significant option for constrained devices, since it consumes fewer resources compared to standard symmetric ciphers, such as AES. Through comprehensive evaluations and comparisons of various symmetric and asymmetric ciphers, this study serves as a blueprint to identify the most efficient ciphers to perform the cryptography operations necessary for deepfake prevention. Full article

In the past decade, a growing number of cyberattacks have been reported, enabling unprecedented levels of personalization, automation, and deception. For instance, recent industry surveys have reported sharp increases in unique social engineering attacks within a single month of 2023, coinciding with the public release of ChatGPT-3.5. This trend highlights how Artificial Intelligence (AI)-powered phishing campaigns have become a significant threat to digital ecosystems. The present study provides an integrative analysis of how generative and deepfake technologies have reshaped the landscape of a Social Engineering (SE) attack, categorizing the main attack strategies and examining their psychological, technological, and ethical implications. In addition, to reviewing enabling technologies, our study conducts a comparative analysis of frameworks and analytical models across technical, empirical, and quantitative perspectives that model AI-driven SE operations and their defensive countermeasures. The convergence of these frameworks reveals three core capabilities—realism, personalization, and automation—that systematically amplify attack efficiency. Building on these insights, the study proposes the Unified Model for AI-Driven Social Engineering (UM-AISE), a conceptual framework that integrates these dimensions across the attack lifecycle and employs a theoretical Markov Decision Process (MDP) analysis. This formalization demonstrates how these capabilities can shift the attacker’s optimal strategy, offering a formal economic perspective distinct from empirical validation. Finally, the study discusses emerging ethical and regulatory challenges associated with AI-mediated deception, highlighting risks related to opacity, accountability, and large-scale manipulation. Taken together, these elements inform evolving approaches for detection, defense, and governance relevant to researchers, policymakers, and practitioners. Full article

As generative speech synthesis produces near-human synthetic voices and reliance on online media grows, robust audio-deepfake detection is essential to fight misuse and misinformation. In this study, we introduce the Arabic Fake Audio Dataset for Modern Standard Arabic (AFAD-MSA), a curated corpus of authentic and synthetic Arabic speech designed to advance research on Arabic deepfake and spoofed-speech detection. The synthetic subset is generated with four state-of-the-art proprietary text-to-speech and voice-conversion models. Rich metadata—covering speaker attributes and generation information—is provided to support reproducibility and benchmarking. To establish reference performance, we trained three AASIST models and compared their performance to two baseline transformer detectors (Wav2Vec 2.0 and Whisper). On the AFAD-MSA test split, AASIST-2 achieved perfect accuracy, surpassing the baseline models. However, its performance declined under cross-dataset evaluation. These results underscore the importance of data construction. Detectors generalize best when exposed to diverse attack types. In addition, continual or contrastive training that interleaves bona fide speech with large, heterogeneous spoofed corpora will further improve detectors’ robustness. Full article

The growing demand for digital content protection has significantly increased the importance of image watermarking, particularly in light of the rising vulnerability of multimedia content to unauthorized modifications. In recent years, research has increasingly focused on leveraging deep learning architectures to enhance watermarking performance, addressing challenges related to transparency, robustness, and payload capacity. Numerous deep learning-based watermarking methods have demonstrated superior effectiveness compared to traditional approaches, particularly those based on Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Transformers, and diffusion models. This paper presents a comprehensive survey of recent developments in both conventional and deep learning-based image watermarking techniques. While traditional methods remain prevalent, deep learning approaches offer notable improvements in embedding and extraction efficiency, particularly when facing complex attacks, including those generated by advanced AI models. Applications in areas such as deepfake detection, cybersecurity, and Internet of Things (IoT) systems highlight the practical significance of these advancements. Despite substantial progress, challenges remain in achieving an optimal balance between invisibility, robustness, and capacity, particularly in high-resolution and real-time scenarios. This study concludes by outlining future research directions toward develop robust, scalable, and efficient deep learning-based watermarking systems capable of addressing emerging threats in digital media environments. Full article

The integrity of digital identity is foundational to a sustainable digital society yet is increasingly challenged by sophisticated AI-enabled risks such as deepfakes and synthetic identities. This is a conceptual paper that develops an AI-integrated, adaptive audit framework for Personal Identity Proofing Services (PIPSs). Focusing on the Republic of Korea’s regime for designating and periodically auditing Accredited Identity Proofing Institutions (AIPIs), this paper proposes an AI-integrated, adaptive audit framework for PIPSs that replaces static, checklist-based oversight with intelligence-driven governance. The framework comprises five capabilities: presentation-attack/synthetic identity detection; anomalous-behavior analytics beyond rule-based fraud detection systems; explainability and bias governance; predictive resilience and incident readiness; and standards conformance for interoperability. To clarify the sustainability relevance, the paper aligns governance outcomes with the UN Sustainable Development Goals (SDGs)—SDG 9 and SDG 16. The paper outlines policy actions and audit-ready indicators to support future pilots and comparative assessment. By shifting from rules to intelligence, the framework strengthens technical resilience and user-centered digital trust, advancing resilient infrastructure and trustworthy institutions. To validate the framework, this study outlines a pilot with AIPIs using SDG-aligned metrics and audit-ready indicators as evaluation endpoints. Full article

The rapid growth of generative artificial intelligence (AI) has enabled diverse applications but also introduced new attack techniques. Similar to deepfake media, generative AI can be exploited to create AI-generated traffic that evades existing intrusion detection systems (IDSs). This paper proposes a Dual Detection System to detect such synthetic network traffic in the Message Queuing Telemetry Transport (MQTT) protocol widely used in Internet of Things (IoT) environments. The system operates in two stages: (i) primary filtering with a Long Short-Term Memory (LSTM) model to detect malicious traffic, and (ii) secondary verification with a Transformer–MLP ensemble to identify AI-generated traffic. Experimental results show that the proposed method achieves an average accuracy of $99.1 \pm 0.6\%$ across different traffic types (normal, malicious, and AI-generated), with nearly 100% detection of synthetic traffic. These findings demonstrate that the proposed dual detection system effectively overcomes the limitations of single-model approaches and significantly enhances detection performance. Full article

Deepfakes, a form of artificial intelligence-generated content, represent a primary method for creating fake cybersecurity threat intelligence (CTI) and are a key source for data poisoning attacks. To effectively assess the authenticity of the cybersecurity threat intelligences (CTIs) in the open-source community, this study presents a novel algorithm for fake-CTI mining, aimed at identifying fake CTIs. Initially, we develop a generalized language model (GLM)-based system for fake CTI generation (GLM-based FCTIG) that adapts a public GLM to the cybersecurity domain using parameter-efficient fine-tuning. We then integrate these fabricated CTIs with authentic ones to simulate data poisoning attacks, evaluating the outcomes of data poisoning attacks from various perspectives. Additionally, we propose a hybrid classification model based on a fine-tuned BERT encoder and a TextCNN head (FCTICM-TC) to discern the authenticity of the CTIs. Finally, a comprehensive FCTICM-TC-based FCTIM method for mining the fake CTIs is presented. The experimental results demonstrate that the proposed GLM-based FCTIG scheme and FCTICM-TC model can effectively generate convincing fake CTI-like texts, while the FCTICM-TC-based FCTIM method is capable of identifying the fake CTIs efficiently. Full article

Facial recognition systems are increasingly used for authentication across domains such as finance, e-commerce, and public services, but their growing adoption raises significant concerns about spoofing attacks enabled by printed photos, replayed videos, or AI-generated deepfakes. To address this gap, we introduce a multi-layered Face Recognition-as-a-Service (FRaaS) platform that integrates passive liveness detection with active challenge–response mechanisms, thereby defending against both low-effort and sophisticated presentation attacks. The platform is designed as a scalable cloud-based solution, complemented by an open-source SDK for seamless third-party integration, and guided by ethical AI principles of fairness, transparency, and privacy. A comprehensive evaluation validates the system’s logic and implementation: (i) Frontend audits using Lighthouse consistently scored above 96% in performance, accessibility, and best practices; (ii) SDK testing achieved over 91% code coverage with reliable OAuth flow and error resilience; (iii) Passive liveness layer employed the DeepPixBiS model, which achieves an Average Classification Error Rate (ACER) of 0.4 on the OULU–NPU benchmark, outperforming prior state-of-the-art methods; and (iv) Load simulations confirmed high throughput (276 req/s), low latency (95th percentile at 1.51 ms), and zero error rates. Together, these results demonstrate that the proposed platform is robust, scalable, and trustworthy for security-critical applications. Full article

This review is devoted to a comprehensive analysis of modern forms of information warfare in the context of digitalization and global interconnectedness. The work considers fundamental theoretical foundations—cognitive distortions, mass communication models, network theories and concepts of cultural code. The key tools of information influence are described in detail, including disinformation, the use of botnets, deepfakes, memetic strategies and manipulations in the media space. Particular attention is paid to methods of identifying and neutralizing information threats using artificial intelligence and digital signal processing, including partial digital convolutions, Fourier–Galois transforms, residue number systems and calculations in finite algebraic structures. The ethical and legal aspects of countering information attacks are analyzed, and geopolitical examples are given, demonstrating the peculiarities of applying various strategies. The review is based on a systematic analysis of 592 publications selected from the international databases Scopus, Web of Science and Google Scholar, covering research from fundamental works to modern publications of recent years (2015–2025). It is also based on regulatory legal acts, which ensures a high degree of relevance and representativeness. The results of the review can be used in the development of technologies for monitoring, detecting and filtering information attacks, as well as in the formation of national cybersecurity strategies. Full article

The rapid adoption of Metaverse technologies in healthcare, particularly for elder safety monitoring, has introduced new security challenges related to the authenticity of virtual representations. As healthcare providers increasingly rely on avatars and digital twins to monitor and interact with elderly patients remotely, ensuring the integrity of these virtual entities becomes paramount. This paper introduces SAVE (Securing Avatars in Virtual Environments), an emerging framework that leverages environmental fingerprinting based on Electric Network Frequency (ENF) signals to authenticate avatars and detect potential deepfake attacks in virtual healthcare settings. Unlike conventional authentication methods that rely solely on digital credentials, SAVE anchors virtual entities to the physical world by utilizing the unique temporal and spatial characteristics of ENF signals. We implement and evaluate SAVE in a Microverse-based nursing home environment designed for monitoring elderly individuals living alone. We evaluated SAVE using a prototype system with Raspberry Pi devices and multiple environmental sensors, demonstrating effectiveness across three attack scenarios in a 30-minute experimental window. Through the experimental evaluation of three distinct attack scenarios, unauthorized device attacks, device ID spoofing, and replay attacks using intercepted data, our system demonstrates high detection accuracy with minimal false positives. Results show that by comparing ENF fingerprints embedded in transmitted data with reference ENF signals, SAVE can effectively identify tampering and ensure the authenticity of avatar updates in real time. The SAVE approach enhances the security of virtual healthcare monitoring without requiring additional user intervention, making it particularly suitable for elderly care applications where ease of use is essential. Our findings highlight the potential of physical environmental fingerprints as a robust security layer for virtual healthcare systems, contributing to safer and more trustworthy remote monitoring solutions for vulnerable populations. Full article

Continuous authentication allows devices to keep checking that the active user is still the rightful owner instead of relying on a single login. However, current methods can be tricked by forging faces, revealing personal data, or draining the battery. Additionally, the environment where the user plays a vital role in determining the user’s online security. Thanks to several security attacks, such as impersonation and replay, the user or the device can easily be compromised. We present a lightweight system that pairs face recognition with complex environmental sensing, i.e., the phone validates the user when the surrounding light or noise changes. A convolutional network turns each captured face into a 128-bit code, which is combined with a random “nonce” and protected by hashing. A camera–microphone module monitors light and sound to decide when to sample again, reducing unnecessary checks. We verified the protocol with formal security tools (Scyther v1.1.3.) and confirmed resistance to replay, interception, deepfake, and impersonation attacks. Across 2700 authentication cycles on a Snapdragon 778G testbed, the median decision time decreased from 61.2 ± 3.4 ms to 42.3 ± 2.1 ms (p < 0.01, paired t-test). Data usage per authentication cycle fell by an average of 24.7% ± 1.8%, and mean energy consumption per cycle decreased from 21.3 mJ to 19.8 mJ (∆ = 6.6 mJ, 95% CI: 5.9–7.2). These differences were consistent across varying lighting (≤50, 50–300, >300 lux) and noise conditions (30–55 dB SPL). These results show that smart-sensor-triggered face recognition can offer secure and energy-efficient continuous verification, supporting smart imaging and deep-learning-based face recognition. Full article

Deepfake audio refers to speech that has been synthetically generated or altered through advanced neural network techniques, often with a degree of realism sufficient to convincingly imitate genuine human voices. As these manipulations become increasingly indistinguishable from authentic recordings, they present significant threats to security, undermine media integrity, and challenge the reliability of digital authentication systems. In this study, a robust detection framework is proposed, which leverages the power of self-supervised learning (SSL) and attention-based modeling to identify deepfake audio samples. Specifically, audio features are extracted from input speech using two powerful pretrained SSL models: HuBERT-Large and WavLM-Large. These distinctive features are then integrated through an Attentional Multi-Feature Fusion (AMFF) mechanism. The fused features are subsequently classified using a NeXt-Time Delay Neural Network (NeXt-TDNN) model enhanced with Efficient Channel Attention (ECA), enabling improved temporal and channel-wise feature discrimination. Experimental results show that the proposed method achieves a 0.42% EER and 0.01 min-tDCF on ASVspoof 2019 LA, a 1.01% EER on ASVspoof 2019 PA, and a pooled 6.56% EER on the cross-channel ASVspoof 2021 LA evaluation, thus highlighting its effectiveness for real-world deepfake detection scenarios. Furthermore, on the ASVspoof 5 dataset, the method achieved a 7.23% EER, outperforming strong baselines and demonstrating strong generalization ability. Moreover, the macro-averaged F1-score of 96.01% and balanced accuracy of 99.06% were obtained on the ASVspoof 2019 LA dataset, while the proposed method achieved a macro-averaged F1-score of 98.70% and balanced accuracy of 98.90% on the ASVspoof 2019 PA dataset. On the highly challenging ASVspoof 5 dataset, which includes crowdsourced, non-studio-quality audio, and novel adversarial attacks, the proposed method achieves macro-averaged metrics exceeding 92%, with a precision of 92.07%, a recall of 92.63%, an F1-measure of 92.35%, and a balanced accuracy of 92.63%. Full article