1 code implementation • 17 Jun 2025 • Eyal German, Sagiv Antebi, Edan Habler, Asaf Shabtai, Yuval Elovici
The results demonstrate significant improvements in AUROC scores compared to existing methods, underscoring our method's effectiveness in reliably verifying whether unauthorized watermarked data was used in LLM training.
no code implementations • 17 Jun 2025 • Omri Haller, Yair Meidan, Dudu Mimran, Yuval Elovici, Asaf Shabtai
Our empirical evaluation of ImpReSS's ability to recommend relevant SPCs that can help address issues raised in support conversations shows promising results, including an MRR@1 (and recall@3) of 0. 72 (0. 89) for general problem solving, 0. 82 (0. 83) for information security support, and 0. 85 (0. 67) for cybersecurity troubleshooting.
no code implementations • 16 Jun 2025 • Shahaf David, Yair Meidan, Ido Hersko, Daniel Varnovitzky, Dudu Mimran, Yuval Elovici, Asaf Shabtai
Despite significant advancements in conversational AI, large language model (LLM)-powered chatbots often struggle with personalizing their responses according to individual user characteristics, such as technical expertise, learning style, and communication preferences.
no code implementations • 3 Jun 2025 • Parth Atulbhai Gandhi, Akansha Shukla, David Tayouri, Beni Ifland, Yuval Elovici, Rami Puzis, Asaf Shabtai
Evaluating the security of multi-agent systems (MASs) powered by large language models (LLMs) is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities.
no code implementations • 10 May 2025 • Akansha Shukla, Parth Atulbhai Gandhi, Yuval Elovici, Asaf Shabtai
Our approach leverages transformer models' multi-head attention capabilities to generate SIEM rule embeddings, which are then analyzed using a similarity matching algorithm to identify the top-k most similar rules.
no code implementations • 8 May 2025 • Elad Feldman, Jacob Shams, Dudi Biton, Alfred Chen, Shaoyuan Xie, Satoru Koda, Yisroel Mirsky, Asaf Shabtai, Yuval Elovici, Ben Nassi
To mitigate this risk, we propose Caracetamol, a robust framework designed to enhance the resilience of object detectors against the effects of activated emergency vehicle lighting.
no code implementations • 3 May 2025 • Eran Aizikovich, Dudu Mimran, Edita Grolman, Yuval Elovici, Asaf Shabtai
To ensure that O-RAN's legitimate activity continues, we introduce MARRS (monitoring adversarial RAN reports), a detection framework based on a long-short term memory (LSTM) autoencoder (AE) that learns contextual features across the network to monitor malicious telemetry (also demonstrated in our testbed).
no code implementations • 22 Apr 2025 • Kun Wang, Guibin Zhang, Zhenhong Zhou, Jiahao Wu, Miao Yu, Shiqian Zhao, Chenlong Yin, Jinhu Fu, Yibo Yan, Hanjun Luo, Liang Lin, Zhihao Xu, Haolang Lu, Xinye Cao, Xinyun Zhou, Weifei Jin, Fanci Meng, Shicheng Xu, Junyuan Mao, Yu Wang, Hao Wu, Minghe Wang, Fan Zhang, Junfeng Fang, Wenjie Qu, Yue Liu, Chengwei Liu, Yifan Zhang, Qiankun Li, Chongye Guo, Yalan Qin, Zhaoxin Fan, Kai Wang, Yi Ding, Donghai Hong, Jiaming Ji, Yingxin Lai, Zitong Yu, Xinfeng Li, Yifan Jiang, Yanhui Li, Xinyu Deng, Junlin Wu, Dongxia Wang, Yihao Huang, Yufei Guo, Jen-tse Huang, Qiufeng Wang, Xiaolong Jin, Wenxuan Wang, Dongrui Liu, Yanwei Yue, Wenke Huang, Guancheng Wan, Heng Chang, Tianlin Li, Yi Yu, Chenghao Li, Jiawei Li, Lei Bai, Jie Zhang, Qing Guo, Jingyi Wang, Tianlong Chen, Joey Tianyi Zhou, Xiaojun Jia, Weisong Sun, Cong Wu, Jing Chen, Xuming Hu, Yiming Li, Xiao Wang, Ningyu Zhang, Luu Anh Tuan, Guowen Xu, Jiaheng Zhang, Tianwei Zhang, Xingjun Ma, Jindong Gu, Liang Pang, Xiang Wang, Bo An, Jun Sun, Mohit Bansal, Shirui Pan, Lingjuan Lyu, Yuval Elovici, Bhavya Kailkhura, Yaodong Yang, Hongwei Li, Wenyuan Xu, Yizhou Sun, Wei Wang, Qing Li, Ke Tang, Yu-Gang Jiang, Felix Juefei-Xu, Hui Xiong, XiaoFeng Wang, DaCheng Tao, Philip S. Yu, Qingsong Wen, Yang Liu
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
no code implementations • 26 Jan 2025 • Jacob Shams, Ben Nassi, Satoru Koda, Asaf Shabtai, Yuval Elovici
To counter this phenomenon, and force the use of more costly and sophisticated methods to leverage this vulnerability, we propose a novel countermeasure to improve the confidence of pedestrian detectors in blind spots, raising the max/average confidence of paths generated by our technique by 0. 09 and 0. 05, respectively.
no code implementations • 14 Jan 2025 • Sagiv Antebi, Edan Habler, Asaf Shabtai, Yuval Elovici
Then, the LLM is used to obtain the probabilities of these keywords and calculate their average log-likelihood to determine input text membership, a process we refer to as Tabbing.
no code implementations • 14 Jan 2025 • Dudi Biton, Jacob Shams, Satoru Koda, Asaf Shabtai, Yuval Elovici, Ben Nassi
In this work, we propose the Physical-domain Adversarial Patch Learning Augmentation (PAPLA) framework, a novel end-to-end (E2E) framework that converts adversarial learning from the digital domain to the physical domain using a projector.
no code implementations • CVPR 2025 • Daniel Samira, Edan Habler, Yuval Elovici, Asaf Shabtai
The proliferation of multi-modal generative models has introduced new privacy and security challenges, especially due to the risks of memorization and unintentional disclosure of sensitive information.
no code implementations • 10 Dec 2024 • Yael Itzhakev, Amit Giloni, Yuval Elovici, Asaf Shabtai
These criteria could form the basis for potential detection methods and be integrated into established evaluation metrics for assessing attack's quality Additionally, we introduce a novel technique for perturbing dependent features while maintaining coherence and feature consistency within the sample.
no code implementations • 28 Nov 2024 • Ben Ganon, Alon Zolfi, Omer Hofman, Inderjeet Singh, Hisashi Kojima, Yuval Elovici, Asaf Shabtai
In recent years, conversational large language models (LLMs) have shown tremendous success in tasks such as casual conversation, question answering, and personalized dialogue, making significant advancements in domains like virtual assistance, social interaction, and online customer engagement.
1 code implementation • 20 Aug 2024 • Tom Segal, Asaf Shabtai, Yuval Elovici
A straightforward approach for preventing such exposure is to train a separate model for each access level.
no code implementations • 5 Aug 2024 • Danielle Lavi, Oleg Brodt, Dudu Mimran, Yuval Elovici, Asaf Shabtai
To evaluate our model's performance, we developed a serverless cybersecurity testbed in an AWS cloud environment, which includes two different serverless applications and simulates a variety of attack scenarios that cover the main security threats faced by serverless functions.
no code implementations • 28 Jul 2024 • Nitzan Bitton-Guetta, Aviv Slobodkin, Aviya Maimon, Eliya Habba, Royi Rassin, Yonatan Bitton, Idan Szpektor, Amir Globerson, Yuval Elovici
To study these skills, we present Visual Riddles, a benchmark aimed to test vision and language models on visual riddles requiring commonsense and world knowledge.
no code implementations • 11 Jul 2024 • Beni Ifland, Elad Duani, Rubin Krief, Miro Ohana, Aviram Zilberman, Andres Murillo, Ofir Manor, Ortal Lavi, Hikichi Kenji, Asaf Shabtai, Yuval Elovici, Rami Puzis
Communication network engineering in enterprise environments is traditionally a complex, time-consuming, and error-prone manual process.
no code implementations • 6 Jul 2024 • Yuval Schwartz, Lavi Benshimol, Dudu Mimran, Yuval Elovici, Asaf Shabtai
As the number and sophistication of cyber attacks have increased, threat hunting has become a critical aspect of active security, enabling proactive detection and mitigation of threats before they cause significant harm.
no code implementations • 8 Jun 2024 • Yonatan Amaru, Prasanna Wudali, Yuval Elovici, Asaf Shabtai
Advanced persistent threats (APTs) pose significant challenges for organizations, leading to data breaches, financial losses, and reputational damage.
no code implementations • 30 May 2024 • Ehud Malul, Yair Meidan, Dudu Mimran, Yuval Elovici, Asaf Shabtai
In this paper, we propose GenKubeSec, a comprehensive and adaptive, LLM-based method, which, in addition to detecting a wide variety of KCF misconfigurations, also identifies the exact location of the misconfigurations and provides detailed reasoning about them, along with suggested remediation.
no code implementations • 13 Apr 2024 • Amit Finkman Noah, Avishag Shapira, Eden Bar Kochva, Inbar Maimon, Dudu Mimran, Yuval Elovici, Asaf Shabtai
We also designed a method for reconstructing the developer's original codebase from code segments sent to the code assistant service (i. e., prompts) during the development process, to thoroughly analyze code leakage risks and evaluate the effectiveness of CodeCloak under practical development scenarios.
1 code implementation • 4 Feb 2024 • Oryan Yehezkel, Alon Zolfi, Amit Baras, Yuval Elovici, Asaf Shabtai
In this paper, we present DeSparsify, an attack targeting the availability of vision transformers that use token sparsification mechanisms.
no code implementations • 17 Jan 2024 • Sagiv Antebi, Noam Azulay, Edan Habler, Ben Ganon, Asaf Shabtai, Yuval Elovici
In November 2023, OpenAI introduced a new service allowing users to create custom versions of ChatGPT (GPTs) by using specific instructions and knowledge to guide the model's behavior.
1 code implementation • 3 Dec 2023 • Amit Baras, Alon Zolfi, Yuval Elovici, Asaf Shabtai
However, their dynamic behavior and average-case performance assumption makes them vulnerable to a novel threat vector -- adversarial attacks that target the model's efficiency and availability.
no code implementations • 30 Nov 2023 • Yizhak Vaisman, Gilad Katz, Yuval Elovici, Asaf Shabtai
To protect an organizations' endpoints from sophisticated cyberattacks, advanced detection methods are required.
1 code implementation • 5 Sep 2023 • Dudi Biton, Aditi Misra, Efrat Levy, Jaidip Kotak, Ron Bitton, Roei Schuster, Nicolas Papernot, Yuval Elovici, Ben Nassi
In our examination of the timing side-channel vulnerabilities associated with this algorithm, we identified the potential to enhance decision-based attacks.
no code implementations • 14 Jun 2023 • Omer Hofman, Amit Giloni, Yarin Hayun, Ikuya Morikawa, Toshiya Shimizu, Yuval Elovici, Asaf Shabtai
X-Detect was evaluated in both the physical and digital space using five different attack scenarios (including adaptive attacks) and the COCO dataset and our new Superstore dataset.
no code implementations • ICCV 2023 • Nitzan Bitton-Guetta, Yonatan Bitton, Jack Hessel, Ludwig Schmidt, Yuval Elovici, Gabriel Stanovsky, Roy Schwartz
We introduce WHOOPS!, a new dataset and benchmark for visual commonsense.
Ranked #1 on
Image-to-Text Retrieval
on WHOOPS!
(using extra training data)
no code implementations • 2 Mar 2023 • Jaidip Kotak, Yuval Elovici
To monitor compliance with such policies, it has become essential to distinguish IoT devices permitted within an organization's network from non white listed (unknown) IoT devices.
1 code implementation • CVPR 2024 • Alon Zolfi, Guy Amit, Amit Baras, Satoru Koda, Ikuya Morikawa, Yuval Elovici, Asaf Shabtai
In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task.
no code implementations • 27 Nov 2022 • Ron Bitton, Alon Malach, Amiel Meiseles, Satoru Momiyama, Toshinori Araki, Jun Furukawa, Yuval Elovici, Asaf Shabtai
Model agnostic feature attribution algorithms (such as SHAP and LIME) are ubiquitous techniques for explaining the decisions of complex classification models, such as deep neural networks.
no code implementations • 24 Nov 2022 • Jacob Shams, Ben Nassi, Ikuya Morikawa, Toshiya Shimizu, Asaf Shabtai, Yuval Elovici
In this paper, we present an adaptive framework to watermark a protected model, leveraging the unique behavior present in the model due to a unique random seed initialized during the model training.
no code implementations • 16 Nov 2022 • Avishag Shapira, Ron Bitton, Dan Avraham, Alon Zolfi, Yuval Elovici, Asaf Shabtai
However, none of prior research proposed a misclassification attack on ODs, in which the patch is applied on the target object.
2 code implementations • 23 Aug 2022 • Mosh Levy, Guy Amit, Yuval Elovici, Yisroel Mirsky
By leveraging a set of diverse surrogate models, our method can predict transferability of adversarial examples.
1 code implementation • 25 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.
Ranked #1 on
Common Sense Reasoning
on WinoGAViL
no code implementations • 13 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.
no code implementations • 21 Jan 2022 • Moshe Levy, Guy Amit, Yuval Elovici, Yisroel Mirsky
Deep learning has shown great promise in the domain of medical image analysis.
no code implementations • 16 Jan 2022 • Edan Habler, Ron Bitton, Dan Avraham, Dudu Mimran, Eitan Klevansky, Oleg Brodt, Heiko Lehmann, Yuval Elovici, Asaf Shabtai
Next, we explore the various AML threats associated with O-RAN and review a large number of attacks that can be performed to realize these threats and demonstrate an AML attack on a traffic steering model.
1 code implementation • 21 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.
no code implementations • 24 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.
no code implementations • 14 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).
no code implementations • 5 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.
no code implementations • 30 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.
no code implementations • 15 Jun 2021 • Efrat Levy, Asaf Shabtai, Bogdan Groza, Pal-Stefan Murvay, Yuval Elovici
This mechanism's effectiveness (100% accuracy) is demonstrated in a wide variety of insertion scenarios on a CAN bus prototype.
no code implementations • 13 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.
no code implementations • 2 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.
no code implementations • 10 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.
1 code implementation • 10 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.
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.
no code implementations • 23 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.
no code implementations • 9 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.
no code implementations • 11 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.
no code implementations • 30 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.
no code implementations • 25 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.
no code implementations • 24 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.
1 code implementation • 19 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.
no code implementations • 7 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.
2 code implementations • 11 Sep 2020 • Yushi Cao, David Berend, Palina Tolmach, Guy Amit, Moshe Levy, Yang Liu, Asaf Shabtai, Yuval Elovici
One of the main causes of unfair behavior in age prediction methods lies in the distribution and diversity of the training data.
1 code implementation • 16 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.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
no code implementations • 10 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.
no code implementations • 5 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.
no code implementations • 30 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.
1 code implementation • 18 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.
no code implementations • 5 Mar 2020 • Dvir Cohen, Yisroel Mirsky, Yuval Elovici, Rami Puzis, Manuel Kamp, Tobias Martin, Asaf Shabtai
In this paper, we present DANTE: a framework and algorithm for mining darknet traffic.
no code implementations • 25 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.
no code implementations • 6 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.
no code implementations • 8 Dec 2019 • Yi Xiang Marcus Tan, Yuval Elovici, Alexander Binder
We investigate to what extent alternative variants of Artificial Neural Networks (ANNs) are susceptible to adversarial attacks.
no code implementations • 11 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.
1 code implementation • 10 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
no code implementations • 31 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.
no code implementations • 28 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.
no code implementations • 3 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
no code implementations • 28 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
1 code implementation • 11 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.
no code implementations • 22 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.
no code implementations • 23 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.
2 code implementations • 9 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.
no code implementations • 23 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.
no code implementations • 10 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.
3 code implementations • 25 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.
no code implementations • 14 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.
no code implementations • 6 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.
no code implementations • 19 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.
no code implementations • 10 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
no code implementations • 19 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.
1 code implementation • 2 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
no code implementations • 9 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.
no code implementations • 22 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.