Machine Learning models, in particular Deep Neural Networks (DNNs), have expensive design and development processes, requiring substantial resources to produce a high-quality model (e.g., data collection, long training time, high level of computing capabilities, etc.). This motivates the consideration of DNNs as Intellectual Property (IP), and an attractive target for actors with the incentive to steal the model in order to benefit from the work of its owners. 
In recent years, various methods were suggested to detect models obtained illegitimately from their owners, however they have been shown to fail to demonstrate satisfactory robustness against model extraction attacks.
In this talk, we present an adaptive watermarking framework for machine learning models, leveraging the unique behavior present in a protected model as a result of a unique random seed initialized during the model training. This watermark is used to detect extracted models, which inherit the same unique behavior, indicating an unauthorized usage of the protected model's intellectual property (IP).
First, we show how an initial seed for random number generation as part of model training produces distinct characteristics in the model's decision boundaries, which are inherited by extracted models and present in their decision boundaries, but aren't present in non-extracted models trained on the same data-set with a different seed.
Based on our findings, we suggest the Robust Adaptive Watermarking (RAW) Framework, which utilizes the unique behavior present in the protected and extracted models to generate a watermark key-set and verification model.
We show that the framework is robust to (1) unseen model extraction attacks, and (2) extracted models which undergo a blurring method (e.g., weight pruning).
We evaluate the framework's robustness against a naive attacker (unaware that the model is watermarked), and an informed attacker (who employs blurring strategies to remove watermarked behavior from an extracted model), and achieve AUC values exceeding 0.9.
Finally, we show that the framework is robust to model extraction attacks with different structure and/or architecture than the protected model.
 

Jacob Shams is an M.Sc. student at Ben-Gurion University of the Negev (BGU). His work addresses the security of AI models and systems, model extraction attacks, deep neural network (DNN) watermarking, and robustness of computer vision (CV) models. Jacob is an M.Sc. researcher at Cyber@Ben-Gurion University (CBG) and is working on multiple research projects in the area of AI security. Jacob holds a B.Sc. in Software Engineering from BGU.

The hype of autonomous cars is getting real. Robots in the wild is a tough task. The main issue is an interaction with diverse and complex enviroment.  The evolutions steps are from fixed enviroments (like most robotics to today) to a more flexible less constrained but still somewhat limited in complexity. Also, the reliability is an important parameter. Can the robot do misstakes? 
In this talk we will try to outline the directions of the Robotics.

Dr. Uri Dubin - CEO, more than 20 years working in Computer Vision Worked in Israeli Defense industry and several startup companies. 
CTO at TytoCare startup, that raised $150M. Holds M.Sc in Electrical Engineering, Ph.D. in Neuroscience from the Technion Univ.
 

We see a plethora of deep learning methods, seeking to automatically infer a dense depth image from a single-color input image. This is important if we want to complement LIDAR sensors used in self-driving cars or to enable single-photo applications like image-editing.

Most State-of-the-Art applications these days rely on self-supervision to train deep neural networks to predict high quality depth-from-color.

Although showing promising results, these often do not translate into real world applications that easily. Either because of differences between synthetic data and real data domains or due to the scarcity of real data, limited in size and scale.

In this session, I am going to talk about the journey we had undertaken to develop a system that reconstructs a 3D model of a colon from an optical colonoscopy video for the purpose of increasing polyps' detection rate and raise standard of care.
 

Signa sealing systems co-founder and algorithms team leader at intuitive Surgical, Erez Posner is a machine learning researcher with a track record of developing and deploying state-of-the-art techniques in the fields of Computer Graphics and Computer Vision. Erez's research is primarily focused on cutting-edge techniques for 3D reconstruction, SLAM, and AI-driven video synthesis. Erez holds a BSc and an MSc in Electrical Engineering from Afeka college and Ben Gurion University, respectively.         

With the recent success of generative models like chatGPT and Stable Diffusion it is clear that larger and larger datasets are needed to train those models. Billion or more image datasets like LAION are becoming more popular. With the growth of dataset size so does the challenge to curate and understand the content of those datasets. In this talk I present fastdup, our popular free GitHub tool that is the first tool (to the best of our knowledge) to scale to a billion image dataset. Using fastdup we have analyzed LAION 1B image dataset and share some surprising results. We plan to share a free version of cleaned LAION as a contribution to the computer vision community. Joint work with Dr. Danny Bickson and Prof. Carlos Guetrin from Stanford.

In today's digital era, dynamic business monitoring systems that continuously check for shifts in Key Performance Indicators (KPIs), data, and models are now a necessity. While many algorithms have been suggested for drift detection tasks, they often overlook some of the practical issues of monitoring. In the following talk, we will discuss three difficulties commonly encountered in monitoring tasks and some possible solutions to address them:
1.        Detection of model drift without access to outcome data - In some scenarios, there is no longer access to the dataset used for the training of the model. Without access to the original responses, it is not possible to quantify the expected variability in common model evaluation metrics (such as accuracy, precision, etc.). We suggest testing for model drift using a likelihood test, training a new model using the predictions as offsets, and testing whether the prediction improved significantly.
2.        Cumulative response over time - When monitoring certain attributes, such as auto insurance policy renewals, the actual response of whether the policy was renewed or not arrives with a delay; this can typically take up to 30 days. Therefore, it is difficult to make a direct comparison between the prediction and actual outcomes. To detect model drift, we suggest a test of the cumulative response over time.

3.        Alarm fatigue - Data drift alarm fatigue is a common problem when monitoring data for changes in the distributions of variables. Statistical tests for distribution equality can generate many false alarms as the number of observations increases, leading to alarm fatigue. To address this problem, we propose a three-fold solution based on multiple comparisons adjustments, equivalence testing, and setting business-relevant thresholds using simulations.
 

Tzviel Frostig works as an analytical researcher at Earnix, a leading software company that provides pricing and personalization solutions for financial institutions. In this role, he develops monitoring and reporting solutions that provide valuable insights into the performance of the pricing optimization and personalization algorithms, as well as the performance of financial products and services as they are presented to clients. Tzviel uses various statistical methods and techniques such as data visualization, descriptive statistics, and predictive modeling to analyze large amounts of data, identify trends and patterns, and extract insights from the data. In addition to his work at Earnix, Tzviel is also pursuing a Ph.D in the Statistics Department at Tel-Aviv University, where his research interests lie in the area of selective inference, which deals with making inferences about a population based on a selected subset of data. He is working under the supervision of Professors Ruth Heller and Yoav Benjamini.
 

This is a talk about our paper: “BRUCE: Bundle Recommendation Using Contextualized item Embeddings” that was just published at the RecSys22 conference

In this paper, we adapted NLP Transformers to solve the bundle recommendation task, without any textual data.

Transformers’ success emphasized the importance of the relations between the sentence's words to the meaning of the whole sentence. A bundle is a set of items sold together, we believe that the relations between a bundle’s items are meaningful as well.

In this talk, I will present how we adapted Transformers for modeling bundles, their items, and most importantly - the user preferences towards the two.

Tzoof Avny Brosh is a Senior ML & NLP researcher at Microsoft. 
In the past 7 years, she has been adding NLP capabilities to Office365 products and working on challenges in the fields of summarization, LLMs, tasks extraction, and search. 
Tzoof completed her B.Sc. in Computer Science from Technion and her M.Sc. in Information Systems Engineering (Machine Learning Program) from Ben Gurion University (Cum Laude), Recommended Systems thesis advised by Prof. Bracha Shapira.

At the AI Week conference, Yana will present lessons learnt from an AI Recommendation Product that enables Playtika to personalize game experience.

Recommendation algorithms usually aim to provide the best experience for a given user. However, in certain use cases, naive implementations may result in a greedy behavior which eventually leads to suboptimal performance of the model. In this talk, we will present our modeling approach that enables us to serve both sides of Ziprecruiter’s employment marketplace while recommending the most relevant jobs for job-seekers and the most relevant job-seekers for employers. Specifically, given a job-seeker’s contextual and behavioral data, our framework learns a jobseeker representation that induces a similarity metric between job-seekers and jobs representations, indicating a tendency to apply, by directly optimizing a joint multimodal embedding space using a multi task contrastive loss. Furthermore, the fact that job-seekers embeddings and the jobs embeddings reside on dual latent spaces enabling zero-shot transfer of the model to downstream tasks powering products for both sides of the marketplace. Finally, we will also discuss other implementation considerations as well as relevant business applications.

Nadav Barkai is an engineering manager who leads a mixed team of data scientists and engineers in ZipRecruiter's recommendation group. Nadav has a rich experience in conducting and leading applied machine learning research in a wide variety of areas like recommendation systems, predictive modeling, time series forecasting, and NLP. Nadav holds an MSc in theoretical Physics from Ben-Gurion UniversityNadav Barkai is an engineering manager who leads a mixed team of data scientists and engineers in ZipRecruiter's recommendation group. Nadav has a rich experience in conducting and leading applied machine learning research in a wide variety of areas like recommendation systems, predictive modeling, time series forecasting, and NLP. Nadav holds an MSc in theoretical Physics from Ben-Gurion University