Instrument 26 | D. CERT-In / Cybersecurity / AI Security

ADVISORYADVISORY

CERT-In Advisory - Security Implications of AI Language-Based Applications, 9 May 2023

CERT-In2023AdvisoryTechnology

AI / PRIVACY / CYBER RELEVANCE

Useful operational guidance for LLM use, especially against sharing credentials, financial information or other sensitive data.

AI: Very HighPrivacy: HighCybersecurity: Very High

READ FIRST

  • Security implications and recommended controls for AI language applications
  • monitoring, MFA and incident response

PURVIEW

Addresses the specific security implications of AI language-based applications, including risks arising from prompt manipulation, unsafe outputs, information exposure, misuse and the broader attack surface created when language models are connected to applications and data. For privacy, the advisory is especially relevant where prompts, documents, conversations or connected data sources contain personal or confidential information. It therefore helps security teams and AI developers identify concrete threat scenarios and integrate secure-design, access-control, monitoring and data-protection measures into LLM deployments.

Classification and legal status. Advisory / non-binding technical guidance.

Open document Download PDF Copyright remains with the publishing authority. For informational purposes only.

Read the official document

This browser cannot display the PDF in the page. Open the document or download the PDF.

Keywords

LLM securityprompt injectionAI advisorydata exposure

Source note

CERT-In official advisory verified.

Legal status indicates whether this resource is legislation, delegated regulation, regulatory direction, guidance, policy, research or technical material. Inclusion in this library does not by itself make a document legally binding.

This tool provides research navigation only and does not constitute legal advice or a determination of legal applicability.

Back to the framework library