RFID-ExSim is an experimental dataset designed for studying passive RFID systems under normal operating conditions and in adversarial attack scenarios. The dataset was collected in a controlled laboratory environment using two synchronized ESP32-based MFRC522 RFID readers interacting with twelve passive RFID tags. In total, >400,000 raw RFID read events were recorded and stored in a structured JSONL format with millisecond-level timestamp resolution.

Access control systems rely increasingly on multimodal biometric and behavioral signals to enhance security and robustness against sophisticated attacks. However, when heterogeneous modalities provide conflicting evidence, such as valid biometric credentials accompanied by abnormal behavioral or acoustic patterns, traditional fusion strategies based on static thresholds or majority voting often fail, leading to false alarms or insecure authorization decisions. This paper addresses this critical limitation by proposing a contextual decision-making fusion framework designed to resolve conflicting multimodal evidence at the decision-making level. The proposed approach models access control as a decision-making problem in a context of uncertainty, where independent agents generate modality-specific evidence from authentication channels based on face, voice, and fingerprints. A centralized fusion mechanism integrates heterogeneous results using adaptive reliability weighting and contextual reasoning to resolve conflicts before operational decisions are made. Rather than treating each modality independently, the framework explicitly considers inconsistencies, uncertainties, and situational context when aggregating evidence. The framework is evaluated using public benchmarks, including VGGFace2, VoxCeleb2, and FVC2004, combined with controlled multimodal scenarios that induce conflicting evidence. Experimental results obtained under controlled contradiction scenarios show that the proposed fusion strategy reduces false alarms and improves decision consistency by approximately 18%. These results are interpreted within the scope of controlled multimodal simulations.

Voice phishing (vishing) has emerged as a major vector for social engineering, exploiting the emotional and persuasive aspects of speech to deceive victims. Existing public datasets are often monolingual and lack structured annotations of persuasive intent and interactional structure in telephony scenarios. VISHGUARD is a multilingual synthetic audio corpus designed to advance research on persuasion-sensitive vishing detection. It contains 3,000 simulated phone calls in English, French, and Modern Standard Arabic evenly distributed between fraudulent and legitimate categories. Each sample is annotated across several dimensions, including persuasion strategy, interactional markers, and emotional tone. The audio recordings were synthetically generated using text-to-speech synthesis and controlled noise mixing, with ambient sounds used to approximate office, street, and home-like acoustic variability rather than full telecommunication-channel effects. The dataset covers durations from 10 to 90 seconds and maintains balanced linguistic and class distributions. VISHGUARD provides a reproducible, script-conditioned synthetic telephony corpus with multidimensional annotations to support controlled research on persuasion-aware vishing detection in multilingual settings. All data files are publicly available to ensure transparency and reuse.

The rapid proliferation of generative models has made deepfake media increasingly realistic and accessible, posing critical threats to digital forensics and multimedia trust. Existing detection methods predominantly rely on single-modality analysis and deterministic predictions, yielding overconfident outputs and limited robustness under ambiguous and cross-dataset conditions. We introduce ARGUS-Net, an uncertainty-aware multi-agent framework for multimodal deepfake detection based on probabilistic evidence fusion. Four independent forensic agents analyzing physiological signals (rPPG), audio-visual synchronization, spectral artifacts, and CNN-based facial manipulation produce modality-specific suspicion and confidence scores. A probabilistic reasoning module fuses this multimodal evidence to estimate deepfake probability and quantify decision uncertainty via Shannon entropy. When uncertainty is high, the ARGUS-AC mechanism triggers controlled perturbations (illumination, motion, and occlusion) to re-evaluate ambiguous cases, reducing mean predictive entropy from 0.985 to 0.935. Decision-making is strictly separated from a post-hoc LLM-based forensic explanation module, ensuring interpretability without affecting the integrity of the detection process. Evaluated on Celeb-DF v2 (AUC = 0.793) and FaceForensics++ (AUC = 0.633), and further assessed on WildDeepfake under a restricted-modality external protocol, ARGUS-Net demonstrates that probabilistic multimodal reasoning combined with active uncertainty resolution improves the reliability of deepfake detection systems while remaining strongly sensitive to domain shift.

Agent-based systems built on large language models (LLMs) increasingly rely on complex internal reasoning processes, tool interactions, and memory mechanisms. However, the internal decision-making dynamics of such agents remain difficult to observe, analyze, and compare in a systematic manner. To address this limitation, we present AgentSec, a curated dataset of structured agent interaction traces designed to support the analysis of agent-level reasoning and action behaviors. The dataset consists of 30 deterministic and non-redundant scenario instances, each capturing a complete agent interaction session under a fixed and validated schema. Quantitatively, the 30 released sessions comprise 67 decision nodes and 45 tool calls (73.3% successful), with provenance graphs exhibiting an average depth of 4.53 (max 7) and a maximum branching factor of 3. Scenarios are organized according to a predefined taxonomy of agent behavioral patterns, including tool success and failure modes, fallback strategies, memory conflicts and overwrites, decision rollbacks, and provenance branching structures. Each scenario encodes a distinct analytical case rather than a parametric variation, enabling focused and interpretable study of agent decision-making processes. AgentSec provides detailed records of decision traces, tool calls, memory updates, and provenance relations, and is intended to facilitate reproducible research on agent behavior analysis, auditing, and evaluation. The dataset is released alongside its schema, scenario manifest, and validation tooling to support reuse and extension by the research community. Rather than serving as a large-scale performance benchmark, AgentSec is explicitly designed as a diagnostic and unit-test suite for auditing agent-level reasoning logic and provenance consistency under controlled structural conditions.

Edge-IoT intrusion detection systems must balance predictive performance with the throughput, latency, and resource constraints of embedded deployment. This study investigates when hardware acceleration is beneficial for tabular IoT intrusion detection on a Raspberry Pi 5 equipped with a Hailo-8 AI accelerator. We evaluate lightweight multilayer perceptrons, conventional 1D convolutional neural networks, and a quantization-friendly 1D-CNN across CICIoT2023 and Edge-IIoTset using ONNX Runtime, Hailo quantized-emulator evaluation, and physical HailoRT benchmarking. The results reveal an execution-regime-dependent acceleration boundary. For the evaluated MLPs, CPU throughput exceeds HailoRT streaming throughput under both reported CPU reference regimes, whereas the conventional 1D-CNNs achieve higher HailoRT streaming throughput than both CPU references. Relative to CPU batch-size-one execution, the CICIoT2023 and Edge-IIoTset 1D-CNNs reach streaming-throughput ratios of 10.34 $$\times $$ and 9.61 $$\times $$ , respectively; the corresponding ratios relative to buffered CPU execution are 1.88 $$\times $$ and 1.82 $$\times $$ . The quantization-friendly model reduces ONNX-to-quantized-emulator macro-F1 degradation by 7.66 percentage points relative to the standard Edge-IIoTset 1D-CNN while also reducing parameter count, HEF on-disk size, and accelerator-side hardware latency. These findings show that accelerator selection for Edge-IoT IDS should consider model structure, execution regime, runtime overhead, and quantization behavior jointly.