The Experts below are selected from a list of 1932 Experts worldwide ranked by ideXlab platform

Lin Jie - One of the best experts on this subject based on the ideXlab platform.

  • use combination of detection systems to reduce errors of judgment on Malicious Request
    Computer Science, 2013
    Co-Authors: Lin Jie
    Abstract:

    Today’s Web application customization technology is widely used.Anomaly detection in early warning and real-time blocking the attack site of application-level program is a very suitable method.However,anomaly detection techniques are easier to detect problems of false positives and false negatives.The use of an integrated system can solve the problem.This integrated system includs the anomaly detection system based anomaly detection system,the Web and a database.Anomaly detection system and the SQL query of a Web serial structure of the anomaly detection system will be able to improve the efficiency of the detection system.The algorithm was evaluated for its applicability on several existing Web application.It is showed that the algorithm is feasible and effective to reduce false positives and false negatives.

Lalit Purohit - One of the best experts on this subject based on the ideXlab platform.

  • web shield a modified firewall to detect Malicious Request
    2012
    Co-Authors: Urjita Thakar, Omprakash Patel, Lalit Purohit
    Abstract:

    In this paper, a novel system (Web Shield) for dynamic detection and filtering of objectionable web content has been presented. Web Shield captures the URL Requested by the client and determines whether it leads to any objectionable content. It is also able to check all child URLs of the Requested URL. It uses simple text matching technique to detect and filter undesired web pages. It uses knowledge base to keep record of objectionable URLs. The proposed system and the existing systems such as browser setting and proxy server based filtering were tested over about 500 web sites. It was observed that proposed system performed much better than existing methods giving about 90% accuracy. This system is very useful for various organizations enabling blocking and filtering of undesired and objectionable web content.

Urjita Thakar - One of the best experts on this subject based on the ideXlab platform.

  • web shield a modified firewall to detect Malicious Request
    2012
    Co-Authors: Urjita Thakar, Omprakash Patel, Lalit Purohit
    Abstract:

    In this paper, a novel system (Web Shield) for dynamic detection and filtering of objectionable web content has been presented. Web Shield captures the URL Requested by the client and determines whether it leads to any objectionable content. It is also able to check all child URLs of the Requested URL. It uses simple text matching technique to detect and filter undesired web pages. It uses knowledge base to keep record of objectionable URLs. The proposed system and the existing systems such as browser setting and proxy server based filtering were tested over about 500 web sites. It was observed that proposed system performed much better than existing methods giving about 90% accuracy. This system is very useful for various organizations enabling blocking and filtering of undesired and objectionable web content.

Laura Falk - One of the best experts on this subject based on the ideXlab platform.

  • An intrusion-tolerant and self-recoverable network service system using a security enhanced chip multiprocessor, in
    2015
    Co-Authors: Weidong Shi, Hsien-hsin S. Lee, Laura Falk
    Abstract:

    This paper proposes a novel system design using a chip multiprocessor (CMP) to provide intrusion tolerance and self-recovery for server applications. Our platform provides three major advantages over previously proposed approaches, 1) security insulation from remote exploits and attacks; 2) close coupling between processor cores in a CMP to ensure immediate logging, fine-grained inspection and fast recov-ery; 3) concurrent and fine-grained inspection, logging and recovery techniques that are off of the critical path. We have designed a multi-point defense and recovery system to de-feat remote exploits. We used a checkpoint based approach to recover server applications under attack. It takes a snap-shot of the application’s context and memory state before it handles the next Request. If the Request turns out to be Malicious, the system can discard the Malicious Request and rollback the application’s state to a known good one through checkpointing. We have also designed an rapid recovery sys-tem for kernel space rootkit attacks. Our intrusion surviv-able and self-recovery design provides reliable production services that System Administrators are seeking. Keywords Intrusion-tolerant computing, survivable service, chip mult

Hitoshi Iyatomi - One of the best experts on this subject based on the ideXlab platform.

  • Web application firewall using character-level convolutional neural network
    2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA), 2018
    Co-Authors: Michiaki Ito, Hitoshi Iyatomi
    Abstract:

    Web applications can be Maliciously exploited by Malicious HTTP Requests. Normally, web application firewall (WAF) protects web applications from known attacks using pattern matching method. However, introduction of WAF is usually expensive as it requires the definition of patterns according to the situation. Furthermore, the system cannot block unknown Malicious Request. In this paper, we come up with an efficient machine learning approach to solve these issues. Our approach uses Character-level convolutional neural network (CLCNN) with very large global max-pooling for extracting the feature of HTTP Request and identify it into normal or Malicious Request. We evaluated our system on HTTP DATASET CSIC 2010 dataset and achieved 98.8% of accuracy under 10-fold cross validation and the average processing time per Request was 2.35ms.