Paper year
2021
Paper dossier
On End-to-End White-Box Adversarial Attacks in Music Information Retrieval
Detail viewSimilarity handoff
Review source metadata, abstract, authors, topics, and local similarity context before moving into explanation and ranking views.
Citations
18
Authors
3
Topic labels
3
Source readout
Source and corpus status
Venue
Transactions of the International Society for Music Information Retrieval
Source slug
tismir
Corpus placement
Core corpus
Similarity rows
6
Ranking readout
Where this paper lands in the current run
Run shadow-generalization-product-candidate-ranking-v1Top 50 surfaced
This block uses the same resolved ranking run as Recommended. Ranks here are materialized paper_scores ranks; live Emerging may be reordered by the bounded ML scorer. Family rank is global within each family, but rank is only shown when this paper lands inside the surfaced top 50.
Families present
0
Top 50
0
Run label
shadow-generalization-product-candidate-ranking-v1
Snapshot
source-snapshot-shadow-generalization-v1-20260521
Scope: family global | run rank-83787b91ef
Emerging
No materialized row for this family in the resolved run
This paper did not surface into the current materialized family row set.
Bridge
No materialized row for this family in the resolved run
This paper did not surface into the current materialized family row set.
Under-cited
No materialized row for this family in the resolved run
This paper did not surface into the current materialized family row set.
Abstract
Small adversarial perturbations of input data can drastically change the performance of machine learning systems, thereby challenging their validity. We compare several adversarial attacks targeting an instrument classifier, where for the first time in Music Information Retrieval (MIR) the perturbations are computed directly on the waveform. The attacks can reduce the accuracy of the classifier significantly, while at the same time keeping perturbations almost imperceptible. Furthermore, we show the potential of adversarial attacks being a security issue in MIR by artificially boosting playcounts through an attack on a real-world music recommender system.
Authors
Neighborhood labels
Topics
3 labels
Topic labels are imported metadata and can be noisy; use them as coarse navigation hints, not authoritative classifications.
Adversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsMusic and Audio Processing
Neighbor surface
Similar papers
6 total neighborsEmbedding v1-title-abstract-1536-cleantext-r3
Similar papers use a separately configured neighbor embedding; it may differ from the embedding version used by the current ranked run.
- Music and Audio ProcessingMusic Technology and Sound StudiesDiverse Musicological Studies
- Music and Audio ProcessingMusic Technology and Sound StudiesDiverse Musicological Studies
- Music and Audio ProcessingMusic Technology and Sound StudiesDiverse Musicological Studies
A Case for Reproducibility in MIR: Replication of 'A Highly Robust Audio Fingerprinting System'
0.539Music and Audio ProcessingDigital Humanities and ScholarshipDigital and Traditional Archives ManagementInvestigating the Perceptual Validity of Evaluation Metrics for Automatic Piano Music Transcription
0.538Music and Audio ProcessingMusic Technology and Sound StudiesSpeech and Audio Processing- Music and Audio ProcessingMusic Technology and Sound StudiesDiverse Music Education Insights
Next handoff
Best next moves from here
01
Check recommendation families
Use Recommended to see whether this paper behaves like an emerging or undercited signal in the current ranked feed, or how it appears on the bridge preview / diagnostics view.
02
Inspect nearby topics
Use Trends to understand whether its attached labels are heating up or cooling down inside the curated corpus.
03
Cross-check evaluation baselines
Use Evaluation to compare the dossier readout against citation and recency baselines for the same resolved family run.