Securing Artificial Intelligence (SAI) – Automated Manipulation of Multimedia Identity Representations
Last updated: 7 Jan 2025
Development Stage
Pre-draft
Draft
Published
19 Jun 2023
Scope
This work item covers AI-based techniques for automatically manipulating identity data represented in different media formats, such as audio, video and text (deepfakes). The work item describes the different technical approaches and analyses the threats posed by deepfakes in different attack scenarios. It then provides technical and organisational measures to mitigate these threats and discusses their effectiveness and limitations. © Copyright 2024, ETSI
External Links
[site_reviews_summary assigned_posts=”post_id” hide=”bars,if_empty” text=”{rating} out of {max} stars ({num} reviews)”]
Let the community know
Categorisation
Domain: Horizontal
Scope: AI-specific
Topic: Safety, Security and resilience
Application: Computer vision, NLP
Key Information
Organisation: ETSI
Discussion
[check_original_title]
