all InfoSec news
Two types of dataset poisoning attacks that can corrupt AI system results
March 12, 2023, 12:01 a.m. | techxplore.com
The RISKS Digest catless.ncl.ac.uk
https://techxplore.com/news/2023-03-dataset-poisoning-corrupt-ai-results.html
“The research team calls this type of attack split view poisoning. Testing
showed that such an approach could be used to purchase enough URLs to poison
a large portion of mainstream AI systems, for as little as $10,000.
“There is another way that AI systems could be subverted—y manipulating
data in well-known data repositories such as Wikipedia. This could be done,
the researchers note, by modifying data just prior to regular data dumps,
preventing monitors from spotting the changes …
attack attacks corrupt data large poisoning repositories research researchers results system systems team testing urls well-known wikipedia
More from catless.ncl.ac.uk / The RISKS Digest
EFI IPv6/PXE Security Flaw
3 months, 2 weeks ago |
catless.ncl.ac.uk
Imaging privacy threats from an ambient light sensor
3 months, 2 weeks ago |
catless.ncl.ac.uk
Re: CLEAR wants to scan your face at airports. Privacy experts are worried.
3 months, 2 weeks ago |
catless.ncl.ac.uk
Jobs in InfoSec / Cybersecurity
DevSecOps Engineer
@ Material Bank | Remote
Instrumentation & Control Engineer - Cyber Security
@ ASSYSTEM | Bridgwater, United Kingdom
Security Consultant
@ Tenable | MD - Columbia - Headquarters
Management Consultant - Cybersecurity - Internship
@ Wavestone | Hong Kong, Hong Kong
TRANSCOM IGC - Cybersecurity Engineer
@ IT Partners, Inc | St. Louis, Missouri, United States
Manager, Security Operations Engineering (EMEA)
@ GitLab | Remote, EMEA