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

Mismatch Repair01:20

Mismatch Repair

6.2K
Organisms are capable of detecting and fixing nucleotide mismatches that occur during DNA replication. This sophisticated process requires identifying the new strand and replacing the erroneous bases with correct nucleotides. Mismatch repair is coordinated by many proteins in both prokaryotes and eukaryotes.
The Mutator Protein Family Plays a Key Role in DNA Mismatch Repair
The human genome has more than 3 billion base pairs of DNA per cell. Prior to cell division, that vast amount of genetic...
6.2K
Mismatch Repair01:36

Mismatch Repair

43.5K
Overview
43.5K
Point and Frameshift Mutations01:30

Point and Frameshift Mutations

780
Point mutations are genetic alterations involving the change of a single nucleotide base pair in DNA. Depending on how the alteration affects protein synthesis, they can lead to various consequences.Point mutations fall into the following types:Silent mutations occur when a nucleotide change does not alter the amino acid sequence due to the redundancy of the genetic code. For instance, changing ACC to ACA still encodes threonine, leaving the protein function unaffected. This occurs because...
780
Mutations01:35

Mutations

42.6K
Mutations are changes in the sequence of DNA. These changes can occur spontaneously or they can be induced by exposure to environmental factors. Mutations can be characterized in a number of different ways: whether and how they alter the amino acid sequence of the protein, whether they occur over a small or large area of DNA, and whether they occur in somatic cells or germline cells.
Chromosomal Alterations Are Large-Scale Mutations
While point mutations are changes in a single nucleotide in...
42.6K
Mutations01:39

Mutations

94.3K
Overview
94.3K
Mutations in Microorganisms01:18

Mutations in Microorganisms

479
Mutations are heritable changes in an organism’s genome involving alterations in the base sequence of DNA or RNA. These changes can influence cellular processes and phenotypic traits, potentially transforming the unaltered wild type into a mutant form. Such changes, termed forward mutations, are pivotal in shaping the genetic diversity of organisms.RNA viruses exhibit the highest mutation rates due to the absence of robust proofreading mechanisms during genome replication. In contrast,...
479

You might also read

Related Articles

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

Sort by
Same author

[Experimental study of the eyelid reconstruction in situ with the acellular xenogeneic dermal matrix].

Zhonghua zheng xing wai ke za zhi = Zhonghua zhengxing waike zazhi = Chinese journal of plastic surgery·2007
Same author

[Mutation analysis of GCH1 gene in Chinese patients with dopa responsive dystonia].

Zhonghua yi xue yi chuan xue za zhi = Zhonghua yixue yichuanxue zazhi = Chinese journal of medical genetics·2007
Same author

[Screening and characterization of marine bacteria with antibacterial and cytotoxic activities, and existence of PKS I and NRPS genes in bioactive strains].

Wei sheng wu xue bao = Acta microbiologica Sinica·2007
Same author

[Collateral supply in patients with severe carotid stenosis].

Zhonghua yi xue za zhi·2007
Same author

[Changes of sleep architecture in patients with narcolepsy].

Zhonghua yi xue za zhi·2007
Same author

[Combined anterior and posterior approach for cervical fracture-dislocation with ankylosing spondylitis].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2007

Related Experiment Video

Updated: Jan 9, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

776

GuidedDE: Targeted black-box adversarial attacks via confidence-guided mutation on automatic speech recognition

Jing Li1, Lipeng Song2, Yanru Feng3

  • 1The School of Computer Science and Technology, North University of China, Taiyuan, 030051, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 1, 2025
PubMed
Summary

We developed Guided Differential Evolution (Guided DE) to improve black-box adversarial attacks on Automatic Speech Recognition (ASR) systems. This method significantly reduces query consumption and reveals phonetic vulnerabilities for more robust ASR security.

Keywords:
Adversarial attackAutomatic speech recognitionBlack-boxDifferential evolution algorithmNeural network

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

994
The Lambda Select cII Mutation Detection System
07:08

The Lambda Select cII Mutation Detection System

Published on: April 26, 2018

8.3K

Related Experiment Videos

Last Updated: Jan 9, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

776
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

994
The Lambda Select cII Mutation Detection System
07:08

The Lambda Select cII Mutation Detection System

Published on: April 26, 2018

8.3K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Cybersecurity

Background:

  • Deep Neural Networks (DNNs) in Automatic Speech Recognition (ASR) are vulnerable to black-box adversarial attacks.
  • Existing genetic algorithm (GA) based methods suffer from high query consumption and limited mechanistic analysis.

Purpose of the Study:

  • To develop a more efficient and insightful black-box adversarial attack method for ASR systems.
  • To reduce query consumption and improve success rates of adversarial attacks.
  • To uncover vulnerability patterns within ASR systems.

Main Methods:

  • Proposed Guided Differential Evolution (Guided DE), a framework combining Differential Evolution (DE) with confidence-driven gradient signals.
  • Integrated population-based search with Connectionist Temporal Classification (CTC) loss feedback.
  • Evaluated Guided DE on three ASR architectures.

Main Results:

  • Guided DE achieved 90-95% success rates for two-word attacks with 40.2k-48.9k queries, improving efficiency by 67-73% over GA baselines.
  • Demonstrated a 2.1-3x increase in success probability compared to GA baselines.
  • Identified that phrases with energy-rich phonemes are 31% more susceptible to attacks.
  • Guided DE improved attack success rates by 62.4% and reduced query costs by 19.3% compared to standard DE.

Conclusions:

  • Guided DE offers an efficient gradient-evolution fusion framework for black-box ASR attacks.
  • The study revealed phonetic vulnerability patterns related to spectral energy dynamics.
  • Findings contribute to developing more robust and secure ASR systems by informing offensive and defensive strategies.