Accuracy Eludes Competitors in Facebook Deepfake Detection Challenge

Ramin Skibba

doi:10.1016/j.eng.2020.10.008

PDF(236 KB)

Engineering ›› 2020, Vol. 6 ›› Issue (12) : 1339-1340. DOI: 10.1016/j.eng.2020.10.008

News & Highlights

Accuracy Eludes Competitors in Facebook Deepfake Detection Challenge

Ramin Skibba

Author information +

History +

Cite this article

EndNote

Ris (Procite)

Bibtex

Download citation ▾

Ramin Skibba. Accuracy Eludes Competitors in Facebook Deepfake Detection Challenge. Engineering, 2020, 6(12): 1339‒1340 https://doi.org/10.1016/j.eng.2020.10.008

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	Skibba R. Media enhanced by artificial intelligence: can we believe anything anymore? Engineering 2020;6(7):723–4.

[2]	Adee S. What are deepfakes and how are they created? [Internet]. New York: IEEE Spectrum; 2020 Apr 29 [cited 2020 Aug 30]. Available from: https:// spectrum.ieee.org/tech-talk/computing/software/what-are-deepfakes-how-arethey-created.

[3]

Ferrer CC, Dolhansky B, Pflaum B, Bitton J, Pan J, Lu J. Deepfake detection challenge results: an open initiative to advance AI [Internet]. Menlo Park: Facebook AI Blog; 2020 Jun 12 [cited 2020 Sep 15]. Available from: https:// ai.facebook.com/blog/deepfake-detection-challenge-results-an-open-initiativeto-advance-ai/.

[4]	Dolhansky B, Bitton J, Pflaum B, Lu J, Howes R, Wang M, et al. The deepfake detection challenge dataset. 2020. arXiv:2006.07397.

[5]	KnightW. Deepfakes aren’t very good. Nor are the tools to detect them [Internet]. San Francisco: Wired; 2020 Jun 12 [cited 2020 Sep 20]. Available from: https:// www.wired.com/story/deepfakes-not-very-good-nor-tools-detect/.

[6]	Manjoo F. How do you know a human wrote this? [Internet]. New York: New York Times; 2020 Jul 29 [cited 2020 Sep 20]. Available from: https://www. nytimes.com/2020/07/29/opinion/gpt-3-ai-automation.html?smid=em-share.

[7]	Brockman G, Murati M, Welinder P; OpenAI. OpenAI API [Internet]. San Francisco: OpenAI; 2020 Jun 11 [cited 2020 Sep 15]. Available from: https:// openai.com/blog/openai-api/.

[8]	Lyu S. Deepfakes and the new AI-generated fake media creation-detection arms race [Internet]. New York: Scientific American; 2020 Jul 20 [cited 2020 Sep 10]. Available from: https://www.scientificamerican.com/article/ detecting-deepfakes1/.

[9]	Dolhansky B, Howes R, Pflaum B, Baram N, Ferrer CC. The deepfake detection challenge (DFDC) preview dataset. 2019. arXiv:1910.08854v2.

[10]	Nguyen TT, Nguyen CM, Nguyen DT, Nguyen DT, Nahavandi S. Deep learning for deepfakes creation and detection: a survey. 2019. arXiv:1909.11573.

[11]	Turek M. Semantic forensics (SemaFor) [Internet]. Arlington: DARPA; c2020 [cited 2020 Sep 10]. Available from: https://www.darpa.mil/program/ semantic-forensics.

[12]	Samanta P, Jain S. E-Witness: preserve and prove forensic soundness of digital evidence. In: Proceedings of the 24th Annual International Conference on Mobile Computing and Networking; 2018 Oct 29–Nov 2; New Delhi, India; 2018. p. 832–4.

[13]	Kelion L. Deepfake detection tool unveiled by Microsoft [Internet]. London: BBC News; 2020 Sep 1 [cited 2020 Sep 25]. Available from: https://www. bbc.com/news/technology-53984114.

[14]	Kelly M. Facebook bans deepfake videos ahead of the 2020 election [Internet]. New York: The Verge; 2020 Jan 7 [cited 2020 Sep 15]. Available from: https:// www.theverge.com/2020/1/7/21054504/facebook-instagram-deepfake-banvideos-nancy-pelosi-congress.

[15]	Robertson A. Twitter will ban ‘deceptive’ faked media that could cause ‘serious harm’ [Internet]. New York: The Verge; 2020 Feb 4 [cited 2020 Sep 15]. Available from: https://www.theverge.com/2020/2/4/21122661/twitterdeepfake-manipulated-media-policy-rollout-date.

[16]	Statt N. TikTok is banning deepfakes to better protect against misinformation [Internet]. New York: The Verge; 2020 Aug 5 [cited 2020 Sep 15]. Available from: https://www.theverge.com/2020/8/5/21354829/tiktok-deepfakes-banmisinformation-us-2020-election-interference.