Recruitment platform detects prompt injection in résumés

2.1%of uploaded résumés contained hidden injection text

0ranking changes attributable to injected instructions after remediation

100%of screening decisions logged with the text the model actually saw

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit case study Report a correction or request removal

Related in Case Studies

Backdoor Attack on Deep Learning Models in Mobile Apps

Deep learning models are increasingly used in mobile applications as critical components. Researchers from Microsoft Research demonstrated that many deep learning models deployed in mobile apps are vulnerable to…

TechnologyModel supply chain assurance

Credo AI Transparency Reports: Facial Recognition Application

A facial recognition service provider used Credo AI's platform to publish transparency reports on the fairness and performance of its identity verification service, in response to customer demand for evidence.

TechnologyCustomer assurance

Face Identification System Evasion via Physical Countermeasures

MITRE's AI Red Team demonstrated a physical-domain evasion attack on a commercial face identification service with the intention of inducing a targeted misclassification. This operation had a combination of…

TechnologyRed teaming programme