Search Results for author: Yuval Elovici

Found 55 papers, 13 papers with code

Transferability Ranking of Adversarial Examples

1 code implementation23 Aug 2022 Mosh Levy, Yuval Elovici, Yisroel Mirsky

However, to the best of our knowledge, there are no works which propose a means for ranking the transferability of an adversarial example in the perspective of a blackbox attacker.

WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models

1 code implementation25 Jul 2022 Yonatan Bitton, Nitzan Bitton Guetta, Ron Yosef, Yuval Elovici, Mohit Bansal, Gabriel Stanovsky, Roy Schwartz

While vision-and-language models perform well on tasks such as visual question answering, they struggle when it comes to basic human commonsense reasoning skills.

Common Sense Reasoning General Knowledge +3

EyeDAS: Securing Perception of Autonomous Cars Against the Stereoblindness Syndrome

no code implementations13 May 2022 Efrat Levy, Ben Nassi, Raz Swissa, Yuval Elovici

The ability to detect whether an object is a 2D or 3D object is extremely important in autonomous driving, since a detection error can have life-threatening consequences, endangering the safety of the driver, passengers, pedestrians, and others on the road.

Autonomous Driving Decision Making +1

The Security of Deep Learning Defences for Medical Imaging

no code implementations21 Jan 2022 Moshe Levy, Guy Amit, Yuval Elovici, Yisroel Mirsky

Deep learning has shown great promise in the domain of medical image analysis.

Adversarial Machine Learning Threat Analysis in Open Radio Access Networks

no code implementations16 Jan 2022 Ron Bitton, Dan Avraham, Eitan Klevansky, Dudu Mimran, Oleg Brodt, Heiko Lehmann, Yuval Elovici, Asaf Shabtai

Motivated by the success of artificial intelligence in other domains, O-RAN strives to leverage machine learning (ML) to automatically and efficiently manage network resources in diverse use cases such as traffic steering, quality of experience prediction, and anomaly detection.

Anomaly Detection BIG-bench Machine Learning

Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Model

1 code implementation21 Nov 2021 Alon Zolfi, Shai Avidan, Yuval Elovici, Asaf Shabtai

In our experiments, we examined the transferability of our adversarial mask to a wide range of FR model architectures and datasets.

Face Recognition Real-World Adversarial Attack

Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples

no code implementations24 Oct 2021 Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Ngai-Man Cheung, Yuval Elovici, Alexander Binder

In this work, we aim to close this gap by studying a conceptually simple approach to defend few-shot classifiers against adversarial attacks.

Dodging Attack Using Carefully Crafted Natural Makeup

no code implementations14 Sep 2021 Nitzan Guetta, Asaf Shabtai, Inderjeet Singh, Satoru Momiyama, Yuval Elovici

Deep learning face recognition models are used by state-of-the-art surveillance systems to identify individuals passing through public areas (e. g., airports).

Face Recognition

Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systems

no code implementations5 Jul 2021 Ron Bitton, Nadav Maman, Inderjeet Singh, Satoru Momiyama, Yuval Elovici, Asaf Shabtai

Using the extension, security practitioners can apply attack graph analysis methods in environments that include ML components; thus, providing security practitioners with a methodological and practical tool for evaluating the impact and quantifying the risk of a cyberattack targeting an ML production system.

BIG-bench Machine Learning Graph Generation

The Threat of Offensive AI to Organizations

no code implementations30 Jun 2021 Yisroel Mirsky, Ambra Demontis, Jaidip Kotak, Ram Shankar, Deng Gelei, Liu Yang, Xiangyu Zhang, Wenke Lee, Yuval Elovici, Battista Biggio

Although offensive AI has been discussed in the past, there is a need to analyze and understand the threat in the context of organizations.

RadArnomaly: Protecting Radar Systems from Data Manipulation Attacks

no code implementations13 Jun 2021 Shai Cohen, Efrat Levy, Avi Shaked, Tair Cohen, Yuval Elovici, Asaf Shabtai

The proposed technique, which allows the detection of malicious manipulation of critical fields in the data stream, is complemented by a timing-interval anomaly detection mechanism proposed for the detection of message dropping attempts.

Anomaly Detection

Who's Afraid of Adversarial Transferability?

no code implementations2 May 2021 Ziv Katzir, Yuval Elovici

By combining theoretical reasoning with a series of empirical results, we show that it is practically impossible to predict whether a given adversarial example is transferable to a specific target model in a black-box setting, hence questioning the validity of adversarial transferability as a real-life attack tool for adversaries that are sensitive to the cost of a failed attack.

BIG-bench Machine Learning

TANTRA: Timing-Based Adversarial Network Traffic Reshaping Attack

no code implementations10 Mar 2021 Yam Sharon, David Berend, Yang Liu, Asaf Shabtai, Yuval Elovici

Prior research on bypassing NIDSs has mainly focused on perturbing the features extracted from the attack traffic to fool the detection system, however, this may jeopardize the attack's functionality.

Network Intrusion Detection

Enhancing Real-World Adversarial Patches through 3D Modeling of Complex Target Scenes

1 code implementation10 Feb 2021 Yael Mathov, Lior Rokach, Yuval Elovici

We use the framework to create a patch for an everyday scene and evaluate its performance using a novel evaluation process that ensures that our results are reproducible in both the digital space and the real world.

Inference Attack Object Reconstruction +1

The Translucent Patch: A Physical and Universal Attack on Object Detectors

no code implementations CVPR 2021 Alon Zolfi, Moshe Kravchik, Yuval Elovici, Asaf Shabtai

Therefore, in our experiments, which are conducted on state-of-the-art object detection models used in autonomous driving, we study the effect of the patch on the detection of both the selected target class and the other classes.

Autonomous Driving object-detection +1

BENN: Bias Estimation Using Deep Neural Network

no code implementations23 Dec 2020 Amit Giloni, Edita Grolman, Tanja Hagemann, Ronald Fromm, Sebastian Fischer, Yuval Elovici, Asaf Shabtai

The need to detect bias in machine learning (ML) models has led to the development of multiple bias detection methods, yet utilizing them is challenging since each method: i) explores a different ethical aspect of bias, which may result in contradictory output among the different methods, ii) provides an output of a different range/scale and therefore, can't be compared with other methods, and iii) requires different input, and therefore a human expert needs to be involved to adjust each method according to the examined model.

Bias Detection

Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering

no code implementations9 Dec 2020 Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Ngai-Man Cheung, Yuval Elovici, Alexander Binder

In this work, we propose a detection strategy to identify adversarial support sets, aimed at destroying the understanding of a few-shot classifier for a certain class.

Toward Scalable and Unified Example-based Explanation and Outlier Detection

no code implementations11 Nov 2020 Penny Chong, Ngai-Man Cheung, Yuval Elovici, Alexander Binder

We compare performances in terms of the classification, explanation quality, and outlier detection of our proposed network with other baselines.

Decision Making Outlier Detection

Being Single Has Benefits. Instance Poisoning to Deceive Malware Classifiers

no code implementations30 Oct 2020 Tzvika Shapira, David Berend, Ishai Rosenberg, Yang Liu, Asaf Shabtai, Yuval Elovici

The performance of a machine learning-based malware classifier depends on the large and updated training set used to induce its model.

Malware Detection

Dynamic Adversarial Patch for Evading Object Detection Models

no code implementations25 Oct 2020 Shahar Hoory, Tzvika Shapira, Asaf Shabtai, Yuval Elovici

In order to demonstrate our attack in a real-world setup, we implemented the patches by attaching flat screens to the target object; the screens are used to present the patches and switch between them, depending on the current camera location.

object-detection Object Detection

Stop Bugging Me! Evading Modern-Day Wiretapping Using Adversarial Perturbations

no code implementations24 Oct 2020 Yael Mathov, Tal Ben Senior, Asaf Shabtai, Yuval Elovici

Our results in the real world suggest that our approach is a feasible solution for privacy protection.

Taking Over the Stock Market: Adversarial Perturbations Against Algorithmic Traders

1 code implementation19 Oct 2020 Elior Nehemya, Yael Mathov, Asaf Shabtai, Yuval Elovici

In this study, we present a realistic scenario in which an attacker influences algorithmic trading systems by using adversarial learning techniques to manipulate the input data stream in real time.

Algorithmic Trading BIG-bench Machine Learning +2

Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examples

no code implementations7 Oct 2020 Yael Mathov, Eden Levy, Ziv Katzir, Asaf Shabtai, Yuval Elovici

We, however, argue that machine learning models trained on heterogeneous tabular data are as susceptible to adversarial manipulations as those trained on continuous or homogeneous data such as images.

BIG-bench Machine Learning

FOOD: Fast Out-Of-Distribution Detector

1 code implementation16 Aug 2020 Guy Amit, Moshe Levy, Ishai Rosenberg, Asaf Shabtai, Yuval Elovici

Deep neural networks (DNNs) perform well at classifying inputs associated with the classes they have been trained on, which are known as in distribution inputs.

OOD Detection Out-of-Distribution Detection

An Automated, End-to-End Framework for Modeling Attacks From Vulnerability Descriptions

no code implementations10 Aug 2020 Hodaya Binyamini, Ron Bitton, Masaki Inokuchi, Tomohiko Yagyu, Yuval Elovici, Asaf Shabtai

Given a description of a security vulnerability, the proposed framework first extracts the relevant attack entities required to model the attack, completes missing information on the vulnerability, and derives a new interaction rule that models the attack; this new rule is integrated within MulVAL attack graph tool.

Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain

no code implementations5 Jul 2020 Ihai Rosenberg, Asaf Shabtai, Yuval Elovici, Lior Rokach

In recent years machine learning algorithms, and more specifically deep learning algorithms, have been widely used in many fields, including cyber security.

Adversarial Attack BIG-bench Machine Learning

Autosploit: A Fully Automated Framework for Evaluating the Exploitability of Security Vulnerabilities

no code implementations30 Jun 2020 Noam Moscovich, Ron Bitton, Yakov Mallah, Masaki Inokuchi, Tomohiko Yagyu, Meir Kalech, Yuval Elovici, Asaf Shabtai

The results show that Autosploit is able to automatically identify the system properties that affect the ability to exploit a vulnerability in both noiseless and noisy environments.

Lightweight Collaborative Anomaly Detection for the IoT using Blockchain

1 code implementation18 Jun 2020 Yisroel Mirsky, Tomer Golomb, Yuval Elovici

Due to their rapid growth and deployment, the Internet of things (IoT) have become a central aspect of our daily lives.

Anomaly Detection

IoT Device Identification Using Deep Learning

no code implementations25 Feb 2020 Jaidip Kotak, Yuval Elovici

In this study, we applied deep learning on network traffic to automatically identify IoT devices connected to the network.

Feature Engineering

GIM: Gaussian Isolation Machines

no code implementations6 Feb 2020 Guy Amit, Ishai Rosenberg, Moshe Levy, Ron Bitton, Asaf Shabtai, Yuval Elovici

In many cases, neural network classifiers are likely to be exposed to input data that is outside of their training distribution data.

General Classification Sentiment Analysis

Why Blocking Targeted Adversarial Perturbations Impairs the Ability to Learn

no code implementations11 Jul 2019 Ziv Katzir, Yuval Elovici

We show that contrary to commonly held belief, the ability to bypass defensive distillation is not dependent on an attack's level of sophistication.

CTRL-ALT-LED: Leaking Data from Air-Gapped Computers via Keyboard LEDs

1 code implementation10 Jul 2019 Mordechai Guri, Boris Zadov, Dima Bykhovsky, Yuval Elovici

In this type of attack, an advanced persistent threat (APT) uses the keyboard LEDs (Caps-Lock, Num-Lock and Scroll-Lock) to encode information and exfiltrate data from airgapped computers optically.

Cryptography and Security Signal Processing

Privacy-Preserving Detection of IoT Devices Connected Behind a NAT in a Smart Home Setup

no code implementations31 May 2019 Yair Meidan, Vinay Sachidananda, Yuval Elovici, Asaf Shabtai

Today, telecommunication service providers (telcos) are exposed to cyber-attacks executed by compromised IoT devices connected to their customers' networks.

Privacy Preserving

Adversarial Attacks on Remote User Authentication Using Behavioural Mouse Dynamics

no code implementations28 May 2019 Yi Xiang Marcus Tan, Alfonso Iacovazzi, Ivan Homoliak, Yuval Elovici, Alexander Binder

In an attempt to address this gap, we built a set of attacks, which are applications of several generative approaches, to construct adversarial mouse trajectories that bypass authentication models.

BIG-bench Machine Learning

HADES-IoT: A Practical Host-Based Anomaly Detection System for IoT Devices (Extended Version)

no code implementations3 May 2019 Dominik Breitenbacher, Ivan Homoliak, Yan Lin Aung, Nils Ole Tippenhauer, Yuval Elovici

The main advantage of HADES-IoT is its low performance overhead, which makes it suitable for the IoT domain, where state-of-the-art approaches cannot be applied due to their high-performance demands.

Cryptography and Security

Defense Methods Against Adversarial Examples for Recurrent Neural Networks

no code implementations28 Jan 2019 Ishai Rosenberg, Asaf Shabtai, Yuval Elovici, Lior Rokach

Using our methods we were able to decrease the effectiveness of such attack from 99. 9% to 15%.

Cryptography and Security

CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning

1 code implementation11 Jan 2019 Yisroel Mirsky, Tom Mahler, Ilan Shelef, Yuval Elovici

In this paper, we show how an attacker can use deep-learning to add or remove evidence of medical conditions from volumetric (3D) medical scans.

Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spaces

no code implementations22 Nov 2018 Ziv Katzir, Yuval Elovici

We leverage those classifiers to produce a sequence of class labels for each nonperturbed input sample and estimate the a priori probability for a class label change between one activation space and another.

General Classification Image Classification

DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN

no code implementations23 Aug 2018 Swee Kiat Lim, Yi Loo, Ngoc-Trung Tran, Ngai-Man Cheung, Gemma Roig, Yuval Elovici

To the best of our knowledge, our method is the first data augmentation technique focused on improving performance in unsupervised anomaly detection.

Data Augmentation Unsupervised Anomaly Detection

N-BaIoT: Network-based Detection of IoT Botnet Attacks Using Deep Autoencoders

1 code implementation9 May 2018 Yair Meidan, Michael Bohadana, Yael Mathov, Yisroel Mirsky, Dominik Breitenbacher, Asaf Shabtai, Yuval Elovici

The proliferation of IoT devices which can be more easily compromised than desktop computers has led to an increase in the occurrence of IoT based botnet attacks.

Anomaly Detection

Query-Efficient Black-Box Attack Against Sequence-Based Malware Classifiers

no code implementations23 Apr 2018 Ishai Rosenberg, Asaf Shabtai, Yuval Elovici, Lior Rokach

In this paper, we present a generic, query-efficient black-box attack against API call-based machine learning malware classifiers.

CIoTA: Collaborative IoT Anomaly Detection via Blockchain

no code implementations10 Mar 2018 Tomer Golomb, Yisroel Mirsky, Yuval Elovici

However, an anomaly detection model must be trained for a long time in order to capture all benign behaviors.

Anomaly Detection

Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection

3 code implementations25 Feb 2018 Yisroel Mirsky, Tomer Doitshman, Yuval Elovici, Asaf Shabtai

In this paper, we present Kitsune: a plug and play NIDS which can learn to detect attacks on the local network, without supervision, and in an efficient online manner.

Network Intrusion Detection

Detection of Unauthorized IoT Devices Using Machine Learning Techniques

no code implementations14 Sep 2017 Yair Meidan, Michael Bohadana, Asaf Shabtai, Martin Ochoa, Nils Ole Tippenhauer, Juan Davis Guarnizo, Yuval Elovici

Based on the classification of 20 consecutive sessions and the use of majority rule, IoT device types that are not on the white list were correctly detected as unknown in 96% of test cases (on average), and white listed device types were correctly classified by their actual types in 99% of cases.

BIG-bench Machine Learning General Classification

Temporal Pattern Discovery for Accurate Sepsis Diagnosis in ICU Patients

no code implementations6 Sep 2017 Eitam Sheetrit, Nir Nissim, Denis Klimov, Lior Fuchs, Yuval Elovici, Yuval Shahar

Sepsis is a condition caused by the body's overwhelming and life-threatening response to infection, which can lead to tissue damage, organ failure, and finally death.

Generic Black-Box End-to-End Attack Against State of the Art API Call Based Malware Classifiers

no code implementations19 Jul 2017 Ishai Rosenberg, Asaf Shabtai, Lior Rokach, Yuval Elovici

In this paper, we present a black-box attack against API call based machine learning malware classifiers, focusing on generating adversarial sequences combining API calls and static features (e. g., printable strings) that will be misclassified by the classifier without affecting the malware functionality.

BIG-bench Machine Learning

SIPHON: Towards Scalable High-Interaction Physical Honeypots

no code implementations10 Jan 2017 Juan Guarnizo, Amit Tambe, Suman Sankar Bhunia, Martín Ochoa, Nils Tippenhauer, Asaf Shabtai, Yuval Elovici

Based on this setup, six physical IP cameras, one NVR and one IP printer are presented as 85 real IoT devices on the Internet, attracting a daily traffic of 700MB for a period of two months.

Cryptography and Security

Handwritten Signature Verification Using Hand-Worn Devices

no code implementations19 Dec 2016 Ben Nassi, Alona Levy, Yuval Elovici, Erez Shmueli

Online signature verification technologies, such as those available in banks and post offices, rely on dedicated digital devices such as tablets or smart pens to capture, analyze and verify signatures.

AirHopper: Bridging the Air-Gap between Isolated Networks and Mobile Phones using Radio Frequencies

1 code implementation2 Nov 2014 Mordechai Guri, Gabi Kedma, Assaf Kachlon, Yuval Elovici

In this paper we present "AirHopper", a bifurcated malware that bridges the air-gap between an isolated network and nearby infected mobile phones using FM signals.

Cryptography and Security

Securing Your Transactions: Detecting Anomalous Patterns In XML Documents

no code implementations9 Sep 2012 Eitan Menahem, Alon Schclar, Lior Rokach, Yuval Elovici

XML transactions are used in many information systems to store data and interact with other systems.

Anomaly Detection

Combining One-Class Classifiers via Meta-Learning

no code implementations22 Dec 2011 Eitan Menahem, Lior Rokach, Yuval Elovici

In particular, we propose two new one-class classification performance measures to weigh classifiers and show that a simple ensemble that implements these measures can outperform the most popular one-class ensembles.

General Classification Meta-Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.