About

Guy Barnhart-Magen

April 1, 2021

Biography

Patents

Academic Publications

Biography

With nearly 25 years of experience in the cyber-security industry, Guy held various positions in both corporates and startups.

In his role as the CTO for the Cyber crisis management firm Profero his focus is making incident response fast and scalable, harnessing the latest technologies and a cloud native approach.


Most recently, he led Intel’s Predictive Threat Analysis group who focused on the security of machine learning systems and trusted execution environments. At Intel, he defined the global AI security strategy and roadmap. He spoke at dozens of events on the research he and the group have done on Security for AI systems and published several whitepapers on the subject.

Guy is the BSidesTLV chairman and CTF lead, a Public speaker in well known global security events (SAS, t2, 44CON, BSidesLV, and several DefCon villages to name a few), and the recipient of the Cisco “black belt” security ninja honor – Cisco’s highest cybersecurity advocate rank.

He started as a software developer for several security startups and later spent eight years in the IDF. After completing his degrees in Electrical Engineering and Applied Mathematics, he focused on security research, in real-world applications.

He joined NDS (later acquired by Cisco). He led the Anti-Hacking, Cryptography, and Supply Chain Security Groups (~25 people in USA and Israel).


For my blog, talks and workshops - please see productsecurity.info

Current

Company Title
Profero Security Profero - CTO and Co-Founder
Melior Security Melior Security - Founder
BSidesTLV BSidesTLV - Chairman, CTF Lead

Past

Company Title Duration
Intel Security Research Manager 2017-2019
Nation-E CTO 2015-2016
Cisco (formerly NDS) Cryptography, Supply Chain Security and Countermeasures Group Manager 2010-2015
HIT B.Sc. in Electrical Engineering (cum laude) and B.Sc. in Applied Mathematics 2006-2010
IDF Executive Officer, Chief Technician 1998-2005

Patents

PROTECTION FOR INFERENCE ENGINE AGAINST MODEL RETRIEVAL ATTACK (July, 2018)

An embodiment of a semiconductor package apparatus may include technology to perform run-time analysis of inputs and outputs of a machine learning model of an inference engine, detect an activity indicative of an attempt to retrieve the machine learning model based on the run-time analysis, and perform one or more preventive actions upon detection of the activity indicative of the attempted model retrieval. Other embodiments are disclosed and claimed.

Publication number: 20190050564

Academic Publications

Active contours: Generalization of the snake mode

Segmentation is one of the fundamental issues in the field of image processing and computer vision. Various approaches include differentiating an object in the image as a final goal or for further processing (medical diagnosis, surveillance, 3-D reconstruction and more). Snakes, a model proposed by Kass, Witkin, and Terzopoulos in 1987, provides an efficient method for segmenting an object through the minimization of its energy. The advantage of snakes is in its ability to use high-level data given by the algorithm operator, as opposed to other methods such as the Laplace technique. The snakes model inherently imposes strong constraints on a given image in order to successfully segment an object. In this paper, the use of adjustment methods is described, which allow us to generalize the snake model to a wider range of applications. Through the use of pre-processing techniques, the model’s constraints were softened. The main theoretical model and its use in facing a real life image is presented.

Research Gate

Differential Diagnostics of Thalassemia Minor by Artificial Neural Networks Model

Current methods used to diagnose the thalassemia minor (TM) patients require high-cost assays, while broader screening based on routine blood count has limited specificity and sensitivity. This study developed a new screening technique for TM patients' diagnosis. The study enrolled 526 patients database that included 185 verified α and β TM cases, and control group consisted of iron-deficiency anemia (IDA), myelodysplastic syndrome (MDS), and healthy patients. More than 1,500 artificial neural networks (ANNs) models were created and the networks that gave high accuracy were selected for the study. TM patients were identified from the general database using the best-optimized ANNs. Comparison between three or six routine blood count parameters determined a slightly higher accuracy of the model with the three-parameter scheme, including mean corpuscular volume, red blood cell distribution width, and red blood cell. Based on these parameters, we were able to separate TM patients from the control group and MDS group, with specificity of 0.967 and sensitivity of 1. Including IDA patients into comparison gave lower but, still, very good values of specificity of 0.968 and sensitivity of 0.9. ANN-based TM diagnostics should be used for broad automatic screening of general population prior diagnosis with high-cost tests." abstract_short = “Current methods used to diagnose the thalassemia minor (TM) patients require high-cost assays, while broader screening based on routine blood count has limited specificity and sensitivity. More than 1,500 artificial neural networks (ANNs) models were created and the networks that gave high accuracy were selected for the study. ANN-based TM diagnostics should be used for broad automatic screening of general population prior diagnosis with high-cost tests.

Research Gate