talk

JARVIS never saw it coming: Hacking machine learning (ML) in speech, text and face recognition - and frankly, everywhere else

Soon to be released publicly Abstract Exploits, Backdoors, and Hacks: words we do not commonly hear when speaking of Machine Learning (ML). In this talk, I will present the relatively new field of hacking and manipulate machine learning systems and the potential these techniques pose for active offensive research. The study of Adversarial ML allows us to leverage the techniques used by these algorithms to find weak points and exploit them in order to achieve:

JARVIS never saw it coming: Hacking machine learning (ML) in speech, text and face recognition - and frankly, everywhere else

Soon to be released publicly Abstract Exploits, Backdoors, and Hacks: words we do not commonly hear when speaking of Machine Learning (ML). In this talk, I will present the relatively new field of hacking and manipulate machine learning systems and the potential these techniques pose for active offensive research. The study of Adversarial ML allows us to leverage the techniques used by these algorithms to find weak points and exploit them in order to achieve:

AppSecIL 2018 CV Workshop

Resources נאום המעלית טיפים לראיון המלצות לכתיבת קורות חיים 1 המלצות לכתיבת קורות חיים 2 Presentation My thanks to Mor Sandosvski for her help and resources!

JARVIS never saw it coming: Hacking machine learning (ML) in speech, text and face recognition - and frankly, everywhere else

Abstract Exploits, Backdoors, and Hacks: words we do not commonly hear when speaking of Machine Learning (ML). In this talk, I will present the relatively new field of hacking and manipulate machine learning systems and the potential these techniques pose for active offensive research. The study of Adversarial ML allows us to leverage the techniques used by these algorithms to find weak points and exploit them in order to achieve:

JARVIS never saw it coming: Hacking machine learning (ML) in speech, text and face recognition - and frankly, everywhere else

Abstract Exploits, Backdoors, and Hacks: words we do not commonly hear when speaking of Machine Learning (ML). In this talk, I will present the relatively new field of hacking and manipulate machine learning systems and the potential these techniques pose for active offensive research. The study of Adversarial ML allows us to leverage the techniques used by these algorithms to find weak points and exploit them in order to achieve:

JARVIS never saw it coming: Hacking machine learning (ML) in speech, text and face recognition - and frankly, everywhere else

Abstract Exploits, Backdoors, and Hacks: words we do not commonly hear when speaking of Machine Learning (ML). In this talk, I will present the relatively new field of hacking and manipulate machine learning systems and the potential these techniques pose for active offensive research. The study of Adversarial ML allows us to leverage the techniques used by these algorithms to find weak points and exploit them in order to achieve:

JARVIS never saw it coming: Hacking machine learning (ML) in speech, text and face recognition - and frankly, everywhere else

Breaking Ground We were happy to share our talk at BSidesLV Breaking Ground floor, and we had a great time, and some excellent feedback! Abstract Exploits, Backdoors, and Hacks: words we do not commonly hear when speaking of Machine Learning (ML). In this talk, I will present the relatively new field of hacking and manipulate machine learning systems and the potential these techniques pose for active offensive research. The study of Adversarial ML allows us to leverage the techniques used by these algorithms to find weak points and exploit them in order to achieve:

Intelligent systems, but are they secure?

Intelligent system, are they secure?

Team8 CISO Delegation presentation on Security for AI

Entrapernursheep, technology and everything between them: hwo did I even get here?

In this talk I covered my journey from my army days all the way to Intel, discussing some of the challenges and decision points along the way, taking some time to explore what I am working on today