Identifying Audio Adversarial Examples via Anomalous Pattern Detection

2020-02-13 · Victor Akinwande, Celia Cintas, Skyler Speakman, Srihari Sridharan

Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar to a benign sample. Given the wide application of DNN-based audio recognition systems, detecting the presence of adversarial examples is of high practical relevance. By applying anomalous pattern detection techniques in the activation space of these models, we show that 2 of the recent and current state-of-the-art adversarial attacks on audio processing systems systematically lead to higher-than-expected activation at some subset of nodes and we can detect these with up to an AUC of 0.98 with no degradation in performance on benign samples.

📄 PDF Abstract BibTeX arXiv:2002.05463

Code (1)

IBM/adversarial-robustness-toolbox 공식 구현 tf

TLDiffGAN: A Latent Diffusion-GAN Framework with Temporal Information Fusion for Anomalous Sound Detection

2026-02-01 · Chengyuan Ma, Peng Jia, Hongyue Guo, Wenming Yang arxiv

Existing generative models for unsupervised anomalous sound detection are limited by their inability to fully capture the complex feature distribution of normal sounds, while the potential of powerful diffusion models in…

MIMII-Agent: Leveraging LLMs with Function Calling for Relative Evaluation of Anomalous Sound Detection

2025-07-28 · Harsh Purohit, Tomoya Nishida, Kota Dohi, Takashi Endo 외 arxiv

This paper proposes a method for generating machine-type-specific anomalies to evaluate the relative performance of unsupervised anomalous sound detection (UASD) systems across different machine types, even in the absenc…

Data Augmentation

Distance metric learning for conditional anomaly detection

2026-05-01 · Michal Valko, Milos Hauskrecht arxiv

Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection framework extends anomaly detection to the problem of identifying ano…

Anomaly Detection Metric Learning

Deep Mining: Detecting Anomalous Patterns in Neural Network Activations with Subset Scanning

2020-01-01 · ICLR 2020 1 · Skyler Speakman, Celia Cintas, Victor Akinwande, Srihari Sridharan 외

This work views neural networks as data generating systems and applies anomalous pattern detection techniques on that data in order to detect when a network is processing a group of anomalous inputs. Detecting anomalies…

Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid Data

2018-04-04 · William Herlands, Edward McFowland III, Andrew Gordon Wilson, Daniel B. Neill

Identifying anomalous patterns in real-world data is essential for understanding where, when, and how systems deviate from their expected dynamics. Yet methods that separately consider the anomalousness of each individua…

Gaussian Processes