Ranking Vulnerability Fixes Using Planning Graph Analysis
Tom Gonda, Rami Puzis, Bracha Shapira, Guy Shani International Workshop on Artificial Intelligence and Security (2017) Link to document During the past years logical attack graphs wereused to find the most critical vulnerabilities anddevise efficient hardening strategies for organizationalnetworks. Most techniques for ranking vulnerabilitieseither do not scale well, e.g. brute-forceattack plan enumeration, or are not […]
Partially Observable Contingent Planning for Penetration Testing
Dorin Shmaryahu, Tom Gonda, Joerg Hoffman, Guy Shani 28th International Workshop on Principles of Diagnosis (DX) (2017) Link to document Penetration Testing (pentesting), where network administratorsautomatically attack their own network to identifyand fix vulnerabilities, has recently received attentionfrom the AI community. Smart algorithms that canidentify robust and efficient attack plans may imitatehuman hackers better than […]
A hybrid approach for improving unsupervised fault detection for robotic systems
Eliahu Khalastchi , Meir Kalech , Lior Rokach Expert Systems with Applications Volume 81, 15 September 2017, Pages 372-383 Link to document The use of robots in our daily lives is increasing. As we rely more on robots, thus it becomes more important for us that the robots will continue on with their mission successfully. […]
Predicting Refractive Surgery Outcome: Machine Learning Approach With Big Data
Cooperation with Soroka University Medical Center Asaf Achiron, Zvi Gur, Uri Aviv, Assaf Hilely, Michael Mimouni, Lily Karmona, Lior Rokach, Igor Kaiserman Journal of Refractive Surgery. 2017;33(9):592-597 Link to document PURPOSE:To develop a decision forest for prediction of laser refractive surgery outcome. METHODS:Data from consecutive cases of patients who underwent LASIK or photorefractive surgeries during […]
Inter-labeler and intra-labeler variability of condition severity classification models using active and passive learning methods
N Nissim, Y Shahar, Y Elovici, G Hripcsak, R Moskovitch Artificial Intelligence in Medicine Volume 81, September 2017, Pages 12-32 Link to document Background and objectives Labeling instances by domain experts for classification is often time consuming and expensive. To reduce such labeling efforts, we had proposed the application of active learning (AL) methods, introduced […]
DLRS 2017: Second Workshop on Deep Learning for Recommender Systems
Cooperation with IBM & Google Balázs Hidasi, Alexandros Karatzoglou, Oren Sar-Shalom, Sander Dieleman, Bracha Shapira, Domonkos Tikk RecSys ’17 Proceedings of the Eleventh ACM Conference on Recommender Systems Pages 370-371 Como, Italy — August 27 – 31, 2017 Link to document Deep learning methods became widely popular in the recommender systems community in 2016, in […]
Acoustic Data Exfiltration from Speakerless Air-Gapped Computers via Covert Hard-Drive Noise (‘DiskFiltration’)
Mordechai Guri Email author , Yosef Solewicz, Andrey Daidakulov, Yuval Elovici ESORICS 2017: Computer Security – ESORICS 2017 pp 98-115 Link to document In the past, it has been shown that malware can exfiltrate data from air-gapped (isolated) networks by transmitting ultrasonic signals via the computer’s speakers. However, such a communication relies on the availability […]
DiskFiltration: Acoustic Data Exfiltration from Speakerless Air-Gapped Computers via Covert Hard-Drive Noise
Cooperation with IDF Mordechai Guri, Yosef Solewicz, Andrey Daidakulov, Yuval Elovici, ESORICS 2017: Computer Security – ESORICS 2017 pp 98-115 Link to document In the past, it has been shown that malware can exfiltrate data from air-gapped (isolated) networks by transmitting ultrasonic signals via the computer’s speakers. However, such a communication relies on the availability […]
I Know What You Saw Last Minute – Encrypted HTTP Adaptive Video Streaming Title Classification
In collaboration with Ariel University R. DubinS, A. DvirPI, O. PelePI and O. HadarPI IEEE Transactions on Information Forensics & Security, Vol. 12, No. 12, pp. 3039-3049, July 2017 Link to document Desktops and laptops can be maliciously exploited to violate privacy. There are two main types of attack scenarios: active and passive. In this […]
Cyber Security and the Role of Intelligent Systems in Addressing its Challenges
Cooperation with Tel-Aviv University Yaniv Harel, Irad Ben Gal and Yuval Elovici ACM Transactions on Intelligent Systems and Technology (TIST) – Special Issue: Cyber Security and Regular Papers archive Volume 8 Issue 4, July 2017 Article No. 49 Link to document We are living in a unique period of history, and the current technology revolution […]
Measurement of online discussion authenticity within online social media
A Elyashar, J Bendahan, R Puzis, MA Sanmateu IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. Link to document In this paper, we propose an approach for estimating the authenticity of online discussions based on the similarity of online social media (OSM) accounts participating in the online discussion to known abusers and […]
9-1-1 DDoS: Attacks, Analysis and Mitigation
Mordechai Guri, Yisroel Mirsky, Yuval Elovici 2017 IEEE European Symposium on Security and Privacy (EuroS&P). Link to document The 911 emergency service belongs to one of the 16 critical infrastructure sectors in the United States. Distributed denial of service (DDoS) attacks launched from a mobile phone botnet pose a significant threat to the availability of […]