admin

June 25, 2021

661
1

Adversa AI Red Team Invented Technology for Ethical Hacking of Facial Recognition Systems

Adversa AI, the leading Trusted AI Research startup, has demonstrated a new attack method on AI facial recognition applications. By making imperceptible changes in human faces, it makes an AI-driven facial recognition algorithm misrecognize persons. Compared to other similar approaches, this method is transferable across all AI models and at ...

Adversarial ML admin / June 23, 2021

Best of Adversarial ML Week 24 – Lip motion patterns secure face liveness detection

Our team makes for you a weekly selection of the best research in the field of artificial intelligence security Securing Face Liveness Detection Using Unforgeable Lip Motion Patterns Deep learning models are used for face authentication, which have high recognition accuracy. However, the weakness of such models is that they ...

June 19, 2021

84
4

4

Company News + Conference Talks admin

Adversa at Machine Learning Week 2021

Alex Polyakov and Eugene Neelou deliver their talks about the state of trusted AI and challenges for securing AI applications at Machine Learning Week Europe Virtual Livestream 2021. The week of June 14th to 18th hundreds of data scientists, analytics managers and AI visionaries from pharma, manufacturing, marketing, insurance, and ...

June 18, 2021

76

Conference Talks + Company News admin

Adversa delivered its research and the latest technologies at CogX Festival 2021

On June 14, the Adversa team presented its research of Trusted AI and the latest technologies at CogX Festival 2021. CogX Festival gathers the brightest minds in business, government and technology to celebrate innovation, discuss global topics and share the latest trends shaping the defining decade ahead. With the ambitious ...

Adversarial ML admin / June 17, 2021

Best of Adversarial ML Week 23 – Detecting adversarial patched objects WITH or WITHOUT signature

Our team makes for you a weekly selection of the best research in the field of artificial intelligence security We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature Recently adversarial patch attacks have been shown to be effective against the object detection based on deep learning. ...

June 14, 2021

86
2

2

Secure AI Weekly admin

Towards trusted AI Week 23 – The way out of Clearview AI database

One of the main problems of AI is the lack of trust from users Is there any way out of Clearview’s facial recognition database? The Verge, June 9, 2021 Last year it became known that the Clearview AI company used millions of images from the Internet to create a facial ...

June 7, 2021

60

Secure AI Weekly admin

Towards trusted AI Week 22 – The annual ML security evasion competition

Artificial intelligence needs comprehensive study Machine Learning Security Evasion Competition 2021 Calls for Researchers and Practitioners Cujo AI, May 31, 2021 The Machine Learning Security Evasion Competition 2021 (MLSEC2021) is an annual event bringing together ML practitioners and security researchers who compete in the defender challenge and the attacker challenge: ...

Secure AI Weekly + Adversarial ML admin / June 2, 2021

Best of Adversarial ML Week 21 – Cross-model adversarial watermark for combating deepfakes

Our team makes for you a weekly selection of the best research in the field of artificial intelligence security CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes Deepfakes have become practically one of the main problems of artificial intelligence technologies and data privacy: with the help of deepfake technologies, ...

May 31, 2021

78

Secure AI Weekly admin

Towards trusted AI Week 21 – Facebook customozes ‘Dynascore’ metric

AI applications need higher accuracy, less biases and more ethics to function properly Facebook Launches An Evaluation-As-A-Service Framework For ML Models Analytics India Magazine, May 30, 2021 Facebook wants to influence the industry to more rigorously evaluate NLP in a real-world setting with a customization of a new ‘Dynascore’ metric. ...