Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice06:11

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice

21.1K
Here, we present a protocol to quantify nest building behavior in mice, which is known to be impaired in several neurological disorders and diseases. This protocol examines the utility of four materials and offers the opportunity to quantify the rater agreement in scoring, improving the validity and reliability of the...
21.1K
Self-Evaluation: Self-Enhancement and Self-Verification03:00

Self-Evaluation: Self-Enhancement and Self-Verification

5.7K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.7K
Indicators02:39

Indicators

59.4K
Certain organic substances change color in dilute solution when the hydronium ion concentration reaches a particular value. For example, phenolphthalein is a colorless substance in any aqueous solution with a hydronium ion concentration greater than 5.0 × 10−9 M (pH < 8.3). In more basic solutions where the hydronium ion concentration is less than 5.0 × 10−9 M (pH > 8.3), it is red or pink. Substances such as phenolphthalein, which can be used to determine the pH of a solution, are...
59.4K
Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat06:27

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat

8.1K
Here, we present a protocol to establish a replicable conductive hearing loss induction via surgical tympanic membrane puncture and verification by otoscope visualization and behavioral assessment by clap...
8.1K
Strategies of Self-Presentation II: Self-Verification01:17

Strategies of Self-Presentation II: Self-Verification

174
Self-verification is a fundamental psychological drive wherein individuals seek affirmation of their self-concept from others, striving for consistency between their internal self-view and external perceptions. This drive operates even when the self-concept is negative, influencing interpersonal behavior and feedback preferences in complex and often counterintuitive ways. Unlike the self-enhancement motive, which seeks positive evaluations, self-verification prioritizes coherence and...
174
Behavioral Characterization of an Angelman Syndrome Mouse Model11:05

Behavioral Characterization of an Angelman Syndrome Mouse Model

5.7K
This manuscript presents a set of highly reproducible behavioral tests to validate an Angelman syndrome mouse...
5.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

PROVGEN: A Privacy-Preserving Approach for Outcome Validation in Genomic Research.

Proceedings on Privacy Enhancing Technologies. Privacy Enhancing Technologies Symposium·2026
Same author

Privacy-Preserving Collaborative Population Stratification with Dynamic Algorithm and Hyperparameter Selection.

ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine·2026
Same author

Privacy-preserving verification of preprocessing in federated learning for genomic data.

JAMIA open·2026
Same author

Explainable drug side effect prediction in central neural system via biologically informed graph neural network.

Translational psychiatry·2026
Same author

Semantically Correct Policy Mining and Enforcement for Attribute based Access Control.

ACM transactions on Internet technology·2026
Same author

Performance Analysis of Dynamic ABAC Systems using a Queuing Theoretic Framework.

Computers & security·2026
Same journal

Blockchain Based Secure Federated Learning With Local Differential Privacy and Incentivization.

IEEE transactions on privacy·2025
Same journal

U.S.-U.K. PETs Prize Challenge: Anomaly Detection via Privacy-Enhanced Federated Learning.

IEEE transactions on privacy·2024
See all related articles
  1. Home
  3. Privacy-preserving Verification Of Ml Preprocessing Via Model Behavior Indicators.
  1. Home
  3. Privacy-preserving Verification Of Ml Preprocessing Via Model Behavior Indicators.

Related Experiment Video

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice
06:11

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice

Published on: October 19, 2019

21.1K

Privacy-Preserving Verification of ML Preprocessing via Model Behavior Indicators.

Wenbiao Li1, Anisa Halimi2, Jaideep Vaidya3

  • 1Case Western Reserve University, Cleveland, OH 44106 USA.

IEEE Transactions on Privacy
|January 19, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

We developed a privacy-preserving method to verify machine learning data preprocessing. This approach uses model behavior analysis to ensure pipeline integrity without needing original data or labels.

Keywords:
Data preprocessingdifferential privacyexplainable AIlocal differential privacymodel auditingtabular data

More Related Videos

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat
06:27

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat

Published on: October 26, 2019

8.1K
Self-Evaluation: Self-Enhancement and Self-Verification
03:00

Self-Evaluation: Self-Enhancement and Self-Verification

5.7K

Related Experiment Videos

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice
06:11

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice

Published on: October 19, 2019

21.1K
Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat
06:27

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat

Published on: October 26, 2019

8.1K
Self-Evaluation: Self-Enhancement and Self-Verification
03:00

Self-Evaluation: Self-Enhancement and Self-Verification

5.7K

Area of Science:

  • Machine Learning
  • Data Privacy
  • Model Verification

Background:

  • Ensuring data preprocessing integrity is crucial for machine learning model reliability, especially with sensitive data.
  • Existing methods often require access to original data or labels, limiting their applicability in privacy-preserving scenarios.

Purpose of the Study:

  • To introduce a novel privacy-preserving framework for verifying the correct application of data preprocessing pipelines.
  • To enable model verification using only black-box access to the trained model, without original training data or ground-truth labels.

Main Methods:

  • The framework combines three behavior indicators: prediction accuracy shifts, Kullback-Leibler (KL) divergence of output distributions, and explanation vectors (LIME/SHAP).
  • It supports both binary correctness decisions and multi-class diagnosis of missing preprocessing steps.
  • A label-free variant utilizes clustering of explanation vectors for verification.

    • Main Results:

    • The binary detector achieved over 75% F1 score even under strong local differential privacy (ε=0.1).
    • Machine-learning classifiers outperformed simple threshold rules for binary classification tasks.
    • Comparable performance was observed between classifiers and threshold rules for multi-class diagnosis.

    Conclusions:

    • The proposed framework offers a practical and scalable solution for safeguarding preprocessing integrity in privacy-sensitive machine learning.
    • The method effectively verifies preprocessing pipelines without compromising data privacy or requiring extensive data access.
    • The label-free variant expands the applicability of the verification method to scenarios lacking labeled pipeline examples.