April 28, 2023, 1:10 a.m. | Nicholas Boucher, Luca Pajola, Ilia Shumailov, Ross Anderson, Mauro Conti

cs.CR updates on arXiv.org arxiv.org

Search engines are vulnerable to attacks against indexing and searching via
text encoding manipulation. By imperceptibly perturbing text using uncommon
encoded representations, adversaries can control results across search engines
for specific search queries. We demonstrate that this attack is successful
against two major commercial search engines - Google and Bing - and one open
source search engine - Elasticsearch. We further demonstrate that this attack
is successful against LLM chat search including Bing's GPT-4 chatbot and
Google's Bard chatbot. We …

adversaries attack attacks bard big big brother bing chat chatbot commercial control elasticsearch encoding engine google gpt gpt-4 llm major manipulation open source results search search engine search engines targeting text uncommon vulnerable

SOC 2 Manager, Audit and Certification

@ Deloitte | US and CA Multiple Locations

Cloud Security Engineer

@ Gainwell Technologies | Any city, OR, US, 99999

Federal Workday Security Lead

@ Accenture Federal Services | Arlington, VA

Workplace Consultant

@ Solvinity | Den Bosch, Noord-Brabant, Nederland

SrMgr-Global Information Security - Security Risk Management

@ Marriott International | Bethesda, MD, United States

Sr. Security Engineer - Data Loss Prevention

@ Verisk | Jersey City, NJ, United States