# VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription

arXiv: https://arxiv.org/abs/2603.07708 · HTML: https://mlsanity.com/paper/2603.07708/

## Key facts

- Cited by 1 papers in the map (data through 7 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding](https://mlsanity.com/paper/1808.05665/) (2018)
- [Pooling Methods in Deep Neural Networks, a Review](https://mlsanity.com/paper/2009.07485/) (2020)
- [RED-ACE: Robust Error Detection for ASR using Confidence Embeddings](https://mlsanity.com/paper/2203.07172/) (2022)
- [Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction](https://mlsanity.com/paper/2505.24347/) (2025)
- [A Practical Survey on Emerging Threats from AI-driven Voice Attacks: How Vulnerable are Commercial Voice Control Systems?](https://mlsanity.com/paper/2312.06010/) (2023)

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

- [Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation](https://mlsanity.com/paper/2605.30031/) (2026)

## Abstract (arXiv)

Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on converting speech to text and then filtering that text, which introduces delays and can ignore important audio cues. This paper introduces VoiceSHIELD-Small, a lightweight model that works in real time. It can transcribe speech and detect whether it is safe or harmful, all in one step. Built on OpenAI's Whisper-small encoder, VoiceSHIELD adds a mean-pooling layer and a simple classification head. It takes just 90-120 milliseconds to classify audio on mid-tier GPUs, while transcription happens at the same time. Tested on a balanced set of 947 audio clips, the model achieved 99.16 percent accuracy and an F1 score of 0.9865. At the default setting, it missed 2.33 percent of harmful inputs. Cross-validation showed consistent performance (F1 standard deviation = 0.0026). The paper also covers the model's design, training data, performance trade-offs, and responsible use guidelines. VoiceSHIELD is released under the MIT license to encourage further research and adoption in voice AI security.