1 Photos and videos
19 Jun 2024
DREW offers a vast range of applications including the detection of AI-generated content and deepfake, protecting ownership of personal media or legal documents, and digital forensics. This can mitigate some of the risks associated with the fast growth of generative AI. 2/
1
1
306
19 Jun 2024
In our previous work (arxiv.org/abs/2310.00076), we exposed the unreliability of watermarking techniques. However, DREW proposes a robust application of watermarks by using a large number of error control bits, ensuring robustness regardless of the severity of attacks. 3/
1
1
271
19 Jun 2024
Read more about our approach and results here:
arxiv.org/abs/2406.02836
Our code is available at:
github.com/mehrdadsaberi/DRE…
1
209
19 Jun 2024
Wonder how to securely🔐trace the source or claim ownership of media (personal, AI-generated, art)? Traditional methods often fail against malicious alterations. Meet DREW: a robust data provenance method combining watermarking and cloud-based retrieval.🧵1/
2
1
8
16,902
Mehrdad Saberi retweeted
3 Oct 2023
AI giants like Google use image watermarking to combat deepfakes
We now show that:
(i) existing methods are quite vulnerable against diffusion, adversarial & spoofing attacks
(ii) imperceptible watermarks can never become reliable
Paper: arxiv.org/abs/2310.00076
A 🧵
4
38
173
44,759