# MAIA: An Inpainting-Based Approach for Music Adversarial Attacks

arXiv: https://arxiv.org/abs/2509.04980 · HTML: https://mlsanity.com/paper/2509.04980/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 17 of 17)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity](https://mlsanity.com/paper/2203.05151/) (2022)
- [Mind the box: l1-APGD for sparse adversarial attacks on image classifiers](https://mlsanity.com/paper/2103.01208/) (2021)
- [Deep Learning and Music Adversaries](https://mlsanity.com/paper/1507.04761/) (2015)
- [Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming](https://mlsanity.com/paper/2211.01317/) (2022)
- [GACELA -- A generative adversarial context encoder for long audio inpainting](https://mlsanity.com/paper/2005.05032/) (2020)
- [Explainability in Music Recommender Systems](https://mlsanity.com/paper/2201.10528/) (2022)
- [Adversarial attacks on Copyright Detection Systems](https://mlsanity.com/paper/1906.07153/) (2019)
- [ByteCover: Cover Song Identification via Multi-Loss Training](https://mlsanity.com/paper/2010.14022/) (2020)
- [ByteCover3: Accurate Cover Song Identification on Short Queries](https://mlsanity.com/paper/2303.11692/) (2023)
- [CoverHunter: Cover Song Identification with Refined Attention and Alignments](https://mlsanity.com/paper/2306.09025/) (2023)
- [Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception](https://mlsanity.com/paper/2207.13192/) (2022)

## Built on by (most cited first, 2 of 2)

- [Diffusion LLMs are Natural Adversaries for any LLM](https://mlsanity.com/paper/2511.00203/) (2025)
- [An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift](https://mlsanity.com/paper/2509.11168/) (2025)

## Abstract (arXiv)

Music adversarial attacks have garnered significant interest in the field of Music Information Retrieval (MIR). In this paper, we present Music Adversarial Inpainting Attack (MAIA), a novel adversarial attack framework that supports both white-box and black-box attack scenarios. MAIA begins with an importance analysis to identify critical audio segments, which are then targeted for modification. Utilizing generative inpainting models, these segments are reconstructed with guidance from the output of the attacked model, ensuring subtle and effective adversarial perturbations. We evaluate MAIA on multiple MIR tasks, demonstrating high attack success rates in both white-box and black-box settings while maintaining minimal perceptual distortion. Additionally, subjective listening tests confirm the high audio fidelity of the adversarial samples. Our findings highlight vulnerabilities in current MIR systems and emphasize the need for more robust and secure models.