Deepfake Offensive Toolkit (real-time deepfakes for virtual cameras)(github.com)
github.com
Deepfake Offensive Toolkit (real-time deepfakes for virtual cameras)
https://github.com/sensity-ai/dot
320 comments
I work at Axis, which makes surveillance cameras.[0] This comment is my own, and is not on behalf of the company. I'm using a throwaway account because I'd rather not be identified (and because surveillance is quite controversial here).
Axis has developed a way to cryptographically sign video, using TPMs (Trusted Platform Module) built into the cameras and embedding the signature into the h.264 stream.[1] The video can be verified on playback using an open-source video player.[2]
I hope this sort of video signing will be mainstream in all cameras in the future (i.e. cellphones etc), as it will pretty much solve the trust issues deep fakes are causing.
[0] https://www.axis.com/ [1] https://www.axis.com/newsroom/article/trust-signed-video [2] https://www.axis.com/en-gb/newsroom/press-release/axis-commu...
Axis has developed a way to cryptographically sign video, using TPMs (Trusted Platform Module) built into the cameras and embedding the signature into the h.264 stream.[1] The video can be verified on playback using an open-source video player.[2]
I hope this sort of video signing will be mainstream in all cameras in the future (i.e. cellphones etc), as it will pretty much solve the trust issues deep fakes are causing.
[0] https://www.axis.com/ [1] https://www.axis.com/newsroom/article/trust-signed-video [2] https://www.axis.com/en-gb/newsroom/press-release/axis-commu...
A few months ago, the IRS made me verify my identity using some janky video conferencing software where I had to hold up a copy of my passport. The software was so hard to use, that I can't believe average people manage to do it. Now, real-time deep fakes are literally easier to create than using the video verification software itself. This will have interesting societal implications.
I'm glad they released this.
I'm sick snd tired of seeing big companies and orgs (Google is the most recent) publish an amazing application of ML but refuse to release the trained model because the model is biased and may be used in a bad way.
I'm sick snd tired of seeing big companies and orgs (Google is the most recent) publish an amazing application of ML but refuse to release the trained model because the model is biased and may be used in a bad way.
To those who ask about the ethics of releasing something like this, I'd say that this technology already exists, and bad actors probably already can get access if they really want to and are sophisticated enough. Making this available to the general public will spread awareness of the existence of such tools, and can then possibly have a preventive effect.
Dot was used for performing vulnerability assessments on many biometric KYC vendors on 2022. The Verge covered this study in this article https://www.theverge.com/2022/5/18/23092964/deepfake-attack-...
Well, genius of this guy. Create the threat then sell the cure. The old school business model we know from anti-virus software.
"I am Cofounder and CEO at Sensity, formerly called Deeptrace, an AI security startup detecting and monitoring online visual threats such as “deepfakes”." (one of the contributors of this repo)
"I am Cofounder and CEO at Sensity, formerly called Deeptrace, an AI security startup detecting and monitoring online visual threats such as “deepfakes”." (one of the contributors of this repo)
I'm really excited to see what could be done with this! I think the primary benefits of this being released are two fold:
1) It will give security researchers more freely available technology to work with in order to try and fight the malicious use of deepfakes. (I saw some interesting comments in this thread about TPM. It'd be interesting to see what other solutions are out there.)
2) It would raise the overall awareness of the general population about the existence and advancements that deepfake technology has made. I would argue that a small subset of the overall population know what the term "deepfake" means, and even fewer are aware at how far it has progressed in only a few short years. (I'm not super well versed in the topic myself, I just know that I've heard a lot of progress has been made.)
I think that since this tech is already actively being used by bad actors, the best course of action that we can take until at least a somewhat good counter to it has been adopted (and then quickly defeated) is to make as many people aware that this is something that could affect them, or their families. That this is something that could be used to get someone fired, or hurt, or killed. I think that the more that people are aware of its existence, the less impactful the overall effect of deepfakes becomes. People learn to look twice before making a call on something, because of how easy it has become to fake audio and video.
1) It will give security researchers more freely available technology to work with in order to try and fight the malicious use of deepfakes. (I saw some interesting comments in this thread about TPM. It'd be interesting to see what other solutions are out there.)
2) It would raise the overall awareness of the general population about the existence and advancements that deepfake technology has made. I would argue that a small subset of the overall population know what the term "deepfake" means, and even fewer are aware at how far it has progressed in only a few short years. (I'm not super well versed in the topic myself, I just know that I've heard a lot of progress has been made.)
I think that since this tech is already actively being used by bad actors, the best course of action that we can take until at least a somewhat good counter to it has been adopted (and then quickly defeated) is to make as many people aware that this is something that could affect them, or their families. That this is something that could be used to get someone fired, or hurt, or killed. I think that the more that people are aware of its existence, the less impactful the overall effect of deepfakes becomes. People learn to look twice before making a call on something, because of how easy it has become to fake audio and video.
To all people who ask moral side of this tech and that it can be abused. What do you think about tools like Kali Linux? NMAP?
Basically any pentesting software can be abused.
Basically any pentesting software can be abused.
Hi there, one of the maintainers here. Thanks for sharing & AMA!
The moral lens people apply to deepfakes feels myopic to me. There are lots of tools that have been built that have arguably done more harm that no one talks about, like port scanning tools. Perhaps because the the negative consequences are so visually obvious and require few intuitive leaps.
Governments and bank branches should offer physical identification as a (potentially payed) service globally, and provide a digital signature that a person is owning a physical device (which should be valid until the device is reset or invalidated by the person).
There is also work going on for deepfake detection challenges since years, I think forensics benchmark was the oldest one and other two placed at 2019 , I dont know if forensics still going on though
http://kaldir.vc.in.tum.de/faceforensics_benchmark/
https://www.kaggle.com/competitions/deepfake-detection-chall...
https://ai.facebook.com/blog/deepfake-detection-challenge-re...
edit*: looks like yes forensics top submission 25 Nov, 2021
http://kaldir.vc.in.tum.de/faceforensics_benchmark/
https://www.kaggle.com/competitions/deepfake-detection-chall...
https://ai.facebook.com/blog/deepfake-detection-challenge-re...
edit*: looks like yes forensics top submission 25 Nov, 2021
I'm absolutely loving the idea of deepfake-detection security SASS developing an easy to use live deepfake system. Crassus tradition is truly immortal.
from the article:
Real-time, controllable deepfakes ready for virtual camera injection. Created for performing penetration testing against e.g. identity verification and video conferencing systems, for the use by security analysts, Red Team members, and biometrics researchers.
Reminds one of the vulnerable world hypothesis. It's only a matter of time before a technology comes along that is both destructive and so simple any fool can use it.
Real-time, controllable deepfakes ready for virtual camera injection. Created for performing penetration testing against e.g. identity verification and video conferencing systems, for the use by security analysts, Red Team members, and biometrics researchers.
Reminds one of the vulnerable world hypothesis. It's only a matter of time before a technology comes along that is both destructive and so simple any fool can use it.
Which requires more computation: a real-time deepfake or real-time deepfake detection? That will determine the future balance of power.
I can imagine more scenarios other than "bad actors" (scammers and such) for this software...
For example: what about using this in an interview for a remote job (possibly intercontinental)? It could tip the balance in some situations (due to biases). For example, beating ageism by projecting a 25 years old version of ourselves. Or removing a tatoo or birth defect (and possibly other changes too, you can imagine).
For example: what about using this in an interview for a remote job (possibly intercontinental)? It could tip the balance in some situations (due to biases). For example, beating ageism by projecting a 25 years old version of ourselves. Or removing a tatoo or birth defect (and possibly other changes too, you can imagine).
Is that something related to the big attack happened last year in China?
https://findbiometrics.com/nine-of-top-10-liveness-detection...
https://findbiometrics.com/nine-of-top-10-liveness-detection...
I predict Kitboga will have a lot of fun with this one...
This is like releasing an app that unlocks all car doors and telling users to only use it on their car.
I see a lot of people decrying its existence, but maybe this tool can help combating deepfakes?
This seems like a good way to get enough attention around deepfakes to make them illegal. How long before a major media personality or politician is catfished by this?
Has anyone followed the install instructions successfully on an m1 mac?
Serious question. What is the chance this video has been deepfaked? https://www.youtube.com/watch?v=ENlL-Uru-cM&ab_channel=CNBCT...
I wished we would be in a position where OBS was not needed.
Just because you think some issues is "inevitable" in the future doesn't mean you should spend academic resources to make it happen faster, while simultaneously making it easier to exploit.
Time for a Teams / Zoom plugin
This is huge!
Anything that can be created, will be created. However, that doesn't free you from all moral culpability. If you create something, make it freely accessible and easy to use, then I think you are partly responsible for its misuse.
I'm not saying that they shouldn't have created this, or that they don't have the right to release it. But to create it, release it, and then pretend that any misuse was entirely separate to you is at best naive.