FrameProv: Towards End-To-End Video Provenance

• URL: http://arxiv.org/abs/2005.09199v1
• Date: Tue, 19 May 2020 03:52:21 GMT
• Title: FrameProv: Towards End-To-End Video Provenance
• Authors: Mansoor Ahmed-Rengers
• Abstract summary: I introduce a long term project that aims to mitigate some of the most egregious forms of manipulation by embedding trustworthy components in the video transmission chain. I present a novel data structure, a video-edit specification language and supporting infrastructure that provides end-to-end video provenance. I am in talks with journalists and video editors to discuss the best ways forward with introducing this idea to the mainstream.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video feeds are often deliberately used as evidence, as in the case of CCTV footage; but more often than not, the existence of footage of a supposed event is perceived as proof of fact in the eyes of the public at large. This reliance represents a societal vulnerability given the existence of easy-to-use editing tools and means to fabricate entire video feeds using machine learning. And, as the recent barrage of fake news and fake porn videos have shown, this isn't merely an academic concern, it is actively been exploited. I posit that this exploitation is only going to get more insidious. In this position paper, I introduce a long term project that aims to mitigate some of the most egregious forms of manipulation by embedding trustworthy components in the video transmission chain. Unlike earlier works, I am not aiming to do tamper detection or other forms of forensics -- approaches I think are bound to fail in the face of the reality of necessary editing and compression -- instead, the aim here is to provide a way for the video publisher to prove the integrity of the video feed as well as make explicit any edits they may have performed. To do this, I present a novel data structure, a video-edit specification language and supporting infrastructure that provides end-to-end video provenance, from the camera sensor to the viewer. I have implemented a prototype of this system and am in talks with journalists and video editors to discuss the best ways forward with introducing this idea to the mainstream.

Related papers

• Authentication and integrity of smartphone videos through multimedia container structure analysis [9.781421596580298]
  This work presents a novel technique to detect possible attacks against MP4, MOV, and 3GP format videos that affect their integrity and authenticity. The objectives of the proposal are to verify the integrity of videos, identify the source of acquisition and distinguish between original and manipulated videos.
  arXiv  Detail & Related papers  (2024-02-05T22:34:24Z)
• Detours for Navigating Instructional Videos [58.1645668396789]
  We propose VidDetours, a video-language approach that learns to retrieve the targeted temporal segments from a large repository of how-to's. We show our model's significant improvements over best available methods for video retrieval and question answering, with recall rates exceeding the state of the art by 35%.
  arXiv  Detail & Related papers  (2024-01-03T16:38:56Z)
• VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models [96.55004961251889]
  Video Instruction Diffusion (VIDiff) is a unified foundation model designed for a wide range of video tasks. Our model can edit and translate the desired results within seconds based on user instructions. We provide convincing generative results for diverse input videos and written instructions, both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2023-11-30T18:59:52Z)
• Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models [65.268245109828]
  Ground-A-Video is a video-to-video translation framework for multi-attribute video editing. It attains temporally consistent editing of input videos in a training-free manner. Experiments and applications demonstrate that Ground-A-Video's zero-shot capacity outperforms other baseline methods in terms of edit-accuracy and frame consistency.
  arXiv  Detail & Related papers  (2023-10-02T11:28:37Z)
• Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts [116.05656635044357]
  We propose a generic video editing framework called Make-A-Protagonist. Specifically, we leverage multiple experts to parse source video, target visual and textual clues, and propose a visual-textual-based video generation model. Results demonstrate the versatile and remarkable editing capabilities of Make-A-Protagonist.
  arXiv  Detail & Related papers  (2023-05-15T17:59:03Z)
• Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models [68.31777975873742]
  Recent attempts at video editing require significant text-to-video data and computation resources for training. We propose vid2vid-zero, a simple yet effective method for zero-shot video editing. Experiments and analyses show promising results in editing attributes, subjects, places, etc., in real-world videos.
  arXiv  Detail & Related papers  (2023-03-30T17:59:25Z)
• Digital Image Forensics using Deep Learning [0.0]
  The aim of our project is to build an algorithm that identifies which camera was used to capture an image using traces of information left intrinsically in the image. Solving this problem would have a big impact on the verification of evidence used in criminal and civil trials and even news reporting.
  arXiv  Detail & Related papers  (2022-10-14T02:27:34Z)
• Efficient video integrity analysis through container characterization [77.45740041478743]
  We introduce a container-based method to identify the software used to perform a video manipulation. The proposed method is both efficient and effective and can also provide a simple explanation for its decisions. It achieves an accuracy of 97.6% in distinguishing pristine from tampered videos and classifying the editing software.
  arXiv  Detail & Related papers  (2021-01-26T14:13:39Z)
• Video Camera Identification from Sensor Pattern Noise with a Constrained ConvNet [7.229968041355052]
  We propose a method to identify the source camera of a video based on camera specific noise patterns that we extract from video frames. Our system is designed to classify individual video frames which are in turn combined by a majority vote to identify the source camera. This work is part of the EU-funded project 4NSEEK focused on forensics against child sexual abuse.
  arXiv  Detail & Related papers  (2020-12-11T12:17:30Z)
• Cost Sensitive Optimization of Deepfake Detector [6.427063076424032]
  We argue that deepfake detection task should be viewed as a screening task, where the user will screen a large number of videos daily. It is clear then that only a small fraction of the uploaded videos are deepfakes, so the detection performance needs to be measured in a cost-sensitive way.
  arXiv  Detail & Related papers  (2020-12-08T04:06:02Z)
• Media Forensics and DeepFakes: an overview [12.333160116225445]
  The boundary between real and synthetic media has become very thin. Deepfakes can be used to manipulate public opinion during elections, commit fraud, discredit or blackmail people. There is an urgent need for automated tools capable of detecting false multimedia content.
  arXiv  Detail & Related papers  (2020-01-18T00:13:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.