You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: Projects/Projects/Video-&-Audio-Provenance-In-The-Age-of-AI.md
+39-34Lines changed: 39 additions & 34 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
---
2
2
title: "Video & Audio Provenance on Arm in the Age of AI"
3
-
description: "Integrating transparent provenance - disclosing whether media is AI-generated or AI-edited, and also what other AI processing has occurred on any media - is necessary for accountability in domains like journalism, security, and regulated industries. This project uses C2PA 2.3 to record such actions as signed, machine-verifiable assertions attached to the asset. This reduces deepfake proliferation and fraud by providing a method to verify provenance. Additionally it tracks authorised and potential unauthorised use of models to analyse the asset."
3
+
description: "Integrating transparent provenance - disclosing whether media is AI-generated or AI-edited, and what other AI processing has occurred on any media - is fundamental for accountability in domains like journalism, security, and regulated industries. This project uses C2PA specification (www.c2pa.org) revision 2.3 to record such actions as signed, machine-verifiable assertions attached to the asset. This reduces deepfake proliferation and fraud by providing a method to verify provenance. Additionally, it tracks authorized and potential unauthorized use of models to analyze the asset, by means of Model Provenance."
4
4
subjects:
5
5
- "ML"
6
6
- "Security"
@@ -18,67 +18,72 @@ support-level:
18
18
publication-date: 2026-02-06
19
19
license:
20
20
status:
21
-
- "Hidden"
21
+
- "Published"
22
22
badges:
23
23
- trending
24
24
- recently_added
25
25
donation:
26
26
---
27
27
28
+
## Description
28
29
29
-
##Description
30
+
### Why is this important?
30
31
31
-
### Why is this important?
32
+
Generative AI has created a trust gap:
33
+
- Images, videos, and audio may be AI-generated or heavily manipulated
34
+
- this can lead to deepfakes, and fraud.
35
+
- This AI-enhancement or editing can occur in real-time - i.e. a person can live stream themselves but use ML to change their appearance and voice.
36
+
- Moreover, the use of AI models to scan images, video, and audio (e.g. facial or voice recognition) is often opaque, with no actual changes to the underlying data.
37
+
- Viewers rarely know whether AI analysis was performed, or what conclusion was reached. Such seamless content transformation, does not require much specialized skills and hence within the reach of common masses.
32
38
33
-
Generative AI has created a trust gap:
34
-
- Images, videos, and audio may be AI-generated or heavily manipulated - this can lead to deepfakes, and fraud.
35
-
- This AI-enhancement or editing can occur in real-time - i.e. a person can livestream themeself, but use ML to change their appearance and voice.
36
-
- Moreover, the use of AI models to scan images, video, and audio (e.g. facial or voice recognition) is often opaque, with no actual changes to the underlying data.
37
-
- Viewers rarely know whether AI analysis was performed, or what conclusion was reached.
38
-
39
-
Integrating transparent provenance - disclosing whether media is AI-generated or AI-edited, and also what other AI processing has occurred on any media - is necessary for accountability in domains like journalism, security, and regulated industries. This project uses C2PA 2.3 to record such actions as signed, machine-verifiable assertions attached to the asset. This reduces deepfake proliferation and fraud by providing a method to verify provenance. Additionally it tracks authorised and potential unauthorised use of models to analyse the asset.
39
+
Integrating transparent provenance - disclosing whether media is AI-generated or AI-edited, and what other AI processing has occurred on any media - is fundamental for accountability in domains like journalism, security, and regulated industries. This project uses C2PA specification (www.c2pa.org) revision 2.3 to record such actions as signed, machine-verifiable assertions attached to the asset. This reduces deepfake proliferation and fraud by providing a method to verify provenance. Additionally, it tracks authorized and potential unauthorized use of models to analyze the asset, by means of Model Provenance.
40
40
41
41
[Arm is a founder member of the C2PA Standards Group.](https://newsroom.arm.com/blog/c2pa-fights-disinformation) The Coalition for Content Provenance and Authenticity (C2PA) specification lets creators and platforms attach cryptographically signed metadata to content like:
42
42
- images 📷
43
43
- videos 🎥
44
44
- audio 🎧
45
45
- documents 📄
46
46
47
-
That metadata can include:
48
-
-who created it
49
-
-what tool was used (camera, Photoshop, generative AI, etc.)
50
-
-what edits were made and when
51
-
-whether AI was involved
47
+
The metadata can include:
48
+
-who created it
49
+
-what tool was used (camera, Photoshop, generative AI, etc.)
50
+
-what edits were made and when
51
+
-whether AI was involved
52
52
53
-
Anyone can later verify this info to see if the content is authentic or has been tampered with.
53
+
Anyone can later verify this info to see if the content is authentic or has been tampered with.
54
54
55
-
The best place to start would be with processing on static audio or video files, but we encourage you to ultimately target a streamed data format - i.e. streamed audio or video, and to perform the inference and record the actions in real-time.
55
+
The best place to start would be with processing on static audio or video files, but we encourage you to ultimately target a streamed data format - i.e. streamed audio or video, and to perform the inference and record the actions in real-time, via attaching provenance information on the streaming content.
56
56
57
-
You should leverage an Arm-powered device, such as a Windows-on-Arm laptop, Apple Silicon MacBook, Arm-powered mobile phone, or Raspberry Pi.
57
+
You should leverage an Arm-powered device, such as a Windows-on-Arm laptop, Apple Silicon MacBook, Arm-powered mobile phone, or Raspberry Pi.
58
58
59
+
### Project Summary
59
60
60
-
### Project Summary
61
+
Build and evaluate a comprehensive AI-augmented audio/video capture and provenance system on an Arm-powered device (e.g. Windows-on-Arm laptop)
62
+
- captures streamed media with a camera or microphone,
63
+
- runs AI models on-device (i.e. face/object/keyword/sentiment detection, upscaling/filters/enhancements),
64
+
- generates C2PA Content Credentials that transparently disclose:
65
+
1. which models were run,
66
+
2. their effect/impact on the image or video
61
67
62
-
Build and evaluate a comprehensive AI-augmented audio/video capture and provenance system on an Arm-powered device (e.g. Windows-on-Arm laptop)
63
-
- captures streamed media with a camera or microphone,
64
-
- runs AI models on-device (i.e. face/object/keyword/sentiment detection, upscaling/filters/enhancements),
65
-
- generates C2PA Content Credentials that transparently disclose:
66
-
1. which models were run,
67
-
2. their effect/impact on the image or video
68
+
and demonstrates how this provenance enables trust and auditability in real-world use cases such as content integrity validation and responsible media pipelines.
68
69
69
-
and demonstrates how this provenance enables trust and auditability in real-world use cases such as content integrity validation and responsible media pipelines.
70
+
You should be able to show your source code, along with documentation/instructions/comments, a short demo video or images to show the project in action, and a short document describing your decisions and how you implemented the project.
70
71
71
-
You should be able to show your source code, along with documentation/instructions/comments, a short demo video or images to show the project in action, and a short document describing your decisions and how you implemented the project.
72
+
## What will you use?
72
73
74
+
You should be willing to learn about, or already familiar with:
75
+
- Programming and building a basic application on your chosen platform/OS
76
+
- C2PA and the concepts behind content provenance and authentication
77
+
- Deploying optimized inference models on Arm-powered CPU via frameworks with KleidiAI integration (e.g. PyTorch).
73
78
74
-
## What will you use?
75
-
You should be willing to learn about, or already familiar with:
76
-
-Programming and building a basic application on your chosen platform/OS
77
-
- C2PA and the concepts behind content provenance and authentication
78
-
-Deploying optimised inference models on Arm-powered CPU via frameworks with KleidiAI integration (e.g. PyTorch)
79
+
80
+
## A few helpful links to relevant items:
81
+
-[Live Video Streaming](https://spec.c2pa.org/specifications/specifications/2.3/specs/C2PA_Specification.html#live-video)
82
+
-[C2PA](https://github.com/contentauth/c2pa-rs)
83
+
-[C-Wrapper for Rust Library](https://gitlab.com/guardianproject/proofmode/simple-c2pa)
79
84
80
85
81
-
## Resources from Arm and our partners
86
+
## Other potentially useful resources from Arm and our partners
82
87
- Repository: [AI on Arm course](https://github.com/arm-university/AI-on-Arm)
83
88
- Arm / Cambridge University edX course: [AI at the Edge on Arm (Mobile)](https://www.edx.org/learn/computer-science/arm-education-ai-at-the-edge-on-arm)
84
89
- Learning Path: [Vision LLM Inference on Android with KleidiAI](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/vision-llm-inference-on-android-with-kleidiai-and-mnn/)
0 commit comments