When AI Audits AI: Securing LLM Deployments with OffSecAI's Prompt Injection Framework
Prompt injection and data exfiltration via model outputs are emerging as critical enterprise risks. Here is how OffSecAI tests them.
OffSecAI · AI Security
Tagged
OffSecAI
1 article
AI security 2cybersecurity compliance 2re-identification risk 1UK GDPR anonymisation 1ICO AI guidance 1membership inference 1model inversion 1motivated intruder test 1synthetic data 1AI training data 1quasi-identifiers 1data protection 1Multi-factor authentication 1types of MFA 1SMS MFA 1TOTP 1Passkeys 1FIDO2 1phishing-resistant MFA 1Identity 1