HomeVulnerabilityAutomated knowledge poisoning proposed as an answer for AI theft risk

Automated knowledge poisoning proposed as an answer for AI theft risk

“Data poisoning has by no means actually labored properly,” stated Bruce Schneier, chief of security structure at Inrupt Inc., and a fellow and lecturer at Harvard’s Kennedy College. “Honeypots, no higher. This can be a intelligent thought, however I don’t see it as being something however an ancillary security system.”

Joseph Steinberg, a US-based cybersecurity and AI marketing consultant, disagreed, saying, “usually this might work for all types of AI and non-AI programs.”

“This isn’t a brand new idea,” he identified. “Some events have been doing this [injecting bad data for defense] with databases for a few years.” For instance, he famous, a database could be watermarked so whether it is stolen and a few of its contents are later used – a faux bank card quantity, for instance — investigators is aware of the place that piece of knowledge got here from. In contrast to watermarking, nevertheless, which places one unhealthy file right into a database, AURA poisons the complete database, so if it’s stolen, it’s ineffective.

See also  Mastercard acquires Recorded Future: How will risk intelligence remodel the funds trade?
- Advertisment -spot_img
RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

- Advertisment -

Most Popular