Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing Detection

• URL: http://arxiv.org/abs/2609.07079v1
• Date: Mon, 07 Sep 2026 06:06:45 GMT
• Title: Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing Detection
• Abstract summary: Domain-invariant prosodic features and self-supervised representations are compared.<n>HuBERT achieves highest performance (94.2% F1, 5-shot), while wav2vec2.0 exhibits a precision-oriented detection profile (90.2% F1 with 99.4% precision, 5-shot)<n>These findings reveal fundamental trade-offs: domain-invariant features enable zero-shot deployment when no real data exists, while SSL methods achieve higher performance but require real samples and compute.
• Score: 5.314238974401925
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Voice phishing detection faces three critical challenges: real criminal recordings are unavailable due to privacy constraints; when available, only a handful of samples exist, insufficient for fine-tuning; and lightweight acoustic-only detection is needed as an alternative to large self-supervised models. We compare domain-invariant prosodic features and self-supervised representations (HuBERT, wav2vec2.0) through cross-domain evaluation-training on scenario-based actor recordings and testing on authentic criminal calls. Domain-invariant prosodic features achieve 69.5% F1 zero-shot and 71.0% with 5-shot learning. HuBERT achieves highest performance (94.2% F1, 5-shot), while wav2vec2.0 exhibits a precision-oriented detection profile (90.2% F1 with 99.4% precision, 5-shot). These findings reveal fundamental trade-offs: domain-invariant features enable zero-shot deployment when no real data exists, while SSL methods achieve higher performance but require real samples and compute.

Related papers

• Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation [43.1212452324751]
  Existing datasets in this domain either entirely lack descriptive text, or suffer from severe text-image semantic misalignment.<n>We present a novel methodology to construct and automatically validate a large-scale multimodal dataset for disaster response.
  arXiv  Detail & Related papers  (2026-07-30T14:23:01Z)
• Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector [0.0]
  We evaluate whether small, open-weight, locally run Vision-Language Models (VLMs) can detect Fast Radio Bursts (FRBs) in dynamic spectra under a zero-shot, prompt-only regime.<n>We show that Gemma 4 2B reaches an accuracy of 93.65%, with no statistically significant difference from SwinYNet.<n>Rewriting the prompt alone reconfigures the same models for three-class FRB/RFI/noise classification on the full set of 3000 spectra, where they reach up to 86% accuracy without a single false FRB.
  arXiv  Detail & Related papers  (2026-07-08T13:15:29Z)
• Prototype-Based Test-Time Adaptation of Vision-Language Models [58.28899599773308]
  Prototype-Based Test-Time Adaptation (PTA)<n>PTA uses a set of class-specific knowledge prototypes to accumulate knowledge from test samples.<n>PTA achieves extremely high efficiency while achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-23T07:20:56Z)
• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage [65.51149575007149]
  We present Fun-DDPS, a generative framework that combines function-space diffusion models with differentiable neural operator surrogates for both forward and inverse modeling.<n>Fun-DDPS produces physically consistent realizations free from the high-frequency artifacts observed in joint-state baselines.
  arXiv  Detail & Related papers  (2026-02-12T18:58:12Z)
• How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study [5.740397289924559]
  No universal winner exists, with detector rankings exhibiting substantial instability.<n>Our findings challenge the one-size-fits-all'' detector paradigm.
  arXiv  Detail & Related papers  (2026-02-08T04:36:13Z)
• Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detection [0.8737375836744933]
  Few-shot prompting has emerged as a practical alternative to fine-tuning for leveraging the capabilities of large language models.<n>We examine retrieval-augmented prompting as a strategy to improve few-shot performance in code vulnerability detection.
  arXiv  Detail & Related papers  (2025-11-28T12:19:31Z)
• Which Sparse Autoencoder Features Are Real? Model-X Knockoffs for False Discovery Rate Control [0.0]
  We introduce Model-X knockoffs to SAE feature selection, using knock-off+ to control the false discovery rate (FDR)<n>Our method offers a re-producible and principled framework for reliable feature discovery by combining SAEs with multiple-testing-aware inference.
  arXiv  Detail & Related papers  (2025-11-12T17:12:45Z)
• FS-IQA: Certified Feature Smoothing for Robust Image Quality Assessment [4.135467749401761]
  We propose a novel certified defense method for Image Quality Assessment (IQA) models.<n>It is based on randomized smoothing with noise applied in the feature space rather than the input space.<n>Our results demonstrate consistent improvements in correlation with subjective quality scores by up to 30.9%.
  arXiv  Detail & Related papers  (2025-08-07T15:47:55Z)
• MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers [41.56951365163419]
  "MixedNUTS" is a training-free method where the output logits of a robust classifier are processed by nonlinear transformations with only three parameters. MixedNUTS then converts the transformed logits into probabilities and mixes them as the overall output. On CIFAR-10, CIFAR-100, and ImageNet datasets, experimental results with custom strong adaptive attacks demonstrate MixedNUTS's vastly improved accuracy and near-SOTA robustness.
  arXiv  Detail & Related papers  (2024-02-03T21:12:36Z)
• Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
  In safety-critical applications of machine learning, it is often desirable for a model to be conservative. We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
  arXiv  Detail & Related papers  (2023-06-08T07:05:36Z)
• (Certified!!) Adversarial Robustness for Free! [116.6052628829344]
  We certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within a 2-norm of 0.5. We obtain these results using only pretrained diffusion models and image classifiers, without requiring any fine tuning or retraining of model parameters.
  arXiv  Detail & Related papers  (2022-06-21T17:27:27Z)
• Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification [54.174146346387204]
  We propose an approach named probabilistic uncertainty guided progressive label refinery (P$2$LR) for domain adaptive person re-identification. A quantitative criterion is established to measure the uncertainty of pseudo labels and facilitate the network training. Our method outperforms the baseline by 6.5% mAP on the Duke2Market task, while surpassing the state-of-the-art method by 2.5% mAP on the Market2MSMT task.
  arXiv  Detail & Related papers  (2021-12-28T07:40:12Z)
• Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications [71.1911136637719]
  We show how provable guarantees can be naturally applied to other real world settings. We show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges.
  arXiv  Detail & Related papers  (2020-06-30T23:33:17Z)

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.