# STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling

arXiv: https://arxiv.org/abs/2603.18103 · HTML: https://mlsanity.com/paper/2603.18103/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 65 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 30 of 45)

- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Spectral Signatures in Backdoor Attacks](https://mlsanity.com/paper/1811.00636/) (2018)
- [STRIP: A Defence Against Trojan Attacks on Deep Neural Networks](https://mlsanity.com/paper/1902.06531/) (2019)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://mlsanity.com/paper/2011.10369/) (2020)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [Adversarial Unlearning of Backdoors via Implicit Hypergradient](https://mlsanity.com/paper/2110.03735/) (2021)
- [Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection](https://mlsanity.com/paper/1908.00686/) (2019)
- [An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks](https://mlsanity.com/paper/2006.08131/) (2020)
- [SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency](https://mlsanity.com/paper/2302.03251/) (2023)
- [Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks](https://mlsanity.com/paper/1911.10312/) (2019)
- [Backdoor Attack against Speaker Verification](https://mlsanity.com/paper/2010.11607/) (2020)
- [The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices](https://mlsanity.com/paper/2209.11715/) (2022)
- [BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models](https://mlsanity.com/paper/2406.17092/) (2024)
- [MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic](https://mlsanity.com/paper/2205.06900/) (2022)
- [Model Agnostic Defence against Backdoor Attacks in Machine Learning](https://mlsanity.com/paper/1908.02203/) (2019)
- [Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency](https://mlsanity.com/paper/2303.18191/) (2023)
- [UNICORN: A Unified Backdoor Trigger Inversion Framework](https://mlsanity.com/paper/2304.02786/) (2023)
- [Can You Hear It? Backdoor Attacks via Ultrasonic Triggers](https://mlsanity.com/paper/2107.14569/) (2021)
- [Rethinking the Reverse-engineering of Trojan Triggers](https://mlsanity.com/paper/2210.15127/) (2022)
- [IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency](https://mlsanity.com/paper/2405.09786/) (2024)
- [Training with More Confidence: Mitigating Injected and Natural Backdoors During Training](https://mlsanity.com/paper/2202.06382/) (2022)
- [Defending Against Backdoor Attacks in Natural Language Generation](https://mlsanity.com/paper/2106.01810/) (2021)
- [Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound](https://mlsanity.com/paper/2307.08208/) (2023)
- [Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics](https://mlsanity.com/paper/2312.02673/) (2023)
- [CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models](https://mlsanity.com/paper/2406.12257/) (2024)
- [REFINE: Inversion-Free Backdoor Defense via Model Reprogramming](https://mlsanity.com/paper/2502.18508/) (2025)
- [Going In Style: Audio Backdoors Through Stylistic Transformations](https://mlsanity.com/paper/2211.03117/) (2022)
- [BadActs: A Universal Backdoor Defense in the Activation Space](https://mlsanity.com/paper/2405.11227/) (2024)

## Built on by (most cited first, 1 of 1)

- [From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents](https://mlsanity.com/paper/2610.15390/) (2026)

## Abstract (arXiv)

With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious threat: an adversary who poisons a small fraction of training data can implant a hidden trigger that controls the model's output while preserving normal behavior on clean inputs. Existing inference-time defenses are not well suited to the audio domain, as they either rely on trigger over-robustness assumptions that fail on transformation-based and semantic triggers, or depend on properties specific to image or text modalities. In this paper, we propose STEP (Stability-based Trigger Exposure Profiling), a black-box, retraining-free backdoor detector that operates under hard-label-only access. Its core idea is to exploit a characteristic dual anomaly of backdoor triggers: anomalous label stability under semantic-breaking perturbations, and anomalous label fragility under semantic-preserving perturbations. STEP profiles each test sample with two complementary perturbation branches that target these two properties respectively, scores the resulting stability features with one-class anomaly detectors trained on benign references, and fuses the two scores via unsupervised weighting. Extensive experiments across seven backdoor attacks show that STEP achieves an average AUROC of 97.92% and EER of 4.54%, substantially outperforming state-of-the-art baselines, and generalizes across model architectures, speech tasks, an open-set verification scenario, and over-the-air physical-world settings.