This site is the archived OWASP Foundation Wiki and is no longer accepting Account Requests.
To view the new OWASP Foundation website, please visit https://owasp.org
Difference between revisions of "OWASP Top 5 Machine Learning Risks"
From OWASP
(Update major parts of the page.. still some sections needs to be updated) (Tag: Visual edit) |
(seba added as co-leader) |
||
| (16 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
<!-- DO NOT ALTER OR REMOVE THE TEXT ON NEXT LINE --> | <!-- DO NOT ALTER OR REMOVE THE TEXT ON NEXT LINE --> | ||
{| style="padding: 0;margin:0;margin-top:10px;text-align:left;" |- | {| style="padding: 0;margin:0;margin-top:10px;text-align:left;" |- | ||
| − | | | + | | style="border-right: 1px dotted gray;padding-right:25px;" valign="top" | |
==The OWASP Top 5 Machine Learning Risks== | ==The OWASP Top 5 Machine Learning Risks== | ||
The idea is to build the required resources which help software security community to understand the emerging technology of machine learning and how it is related to security, warn them about the risk associated with using ML, and discuss the defending techniques. | The idea is to build the required resources which help software security community to understand the emerging technology of machine learning and how it is related to security, warn them about the risk associated with using ML, and discuss the defending techniques. | ||
==Description== | ==Description== | ||
| − | Machine Learning has recently re-emerged as a powerful tool in multiple business sectors | + | Machine Learning has recently re-emerged as a powerful tool in multiple business sectors. It also becomes vital when it is harnessed for the Security services and applications like Fraud Detection, Anomaly Detection, Behavioral Analysis, etc. |
| − | Although these applications have huge success, there are security risks associated with the learning technique especially the security of the learning phase; which can still be vulnerable to threats originated by potential adversaries, and consequently it has considerable impact on their prediction results | + | Although these applications have huge success, there are still security risks associated with the learning technique especially the security of the learning phase; which can still be vulnerable to threats originated by potential adversaries, and consequently it has considerable impact on their prediction results |
This project will list these risks and the defending techniques | This project will list these risks and the defending techniques | ||
| Line 21: | Line 21: | ||
<!-- DO NOT ALTER OR REMOVE THE TEXT ON NEXT LINE --> | <!-- DO NOT ALTER OR REMOVE THE TEXT ON NEXT LINE --> | ||
| − | | | + | | style="padding-left:25px;width:200px;border-right: 1px dotted gray;padding-right:25px;" valign="top" | |
| − | |||
| − | == | + | == Project News == |
| + | June 2018: <br /> | ||
| + | * Project was discussed in Open Security Summit 2018 with wider team. https://open-security-summit.org/tracks/owasp-projects/working-sessions/owasp-top-5-machine-learning-risks/. stay tuned for outcomes. | ||
| + | * The first draft document is now available on Github https://github.com/OWASP/Top-5-Machine-Learning-Risks/ | ||
| + | * Please raise issues in github for any comments or suggestions | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | * | + | March 2018: <br /> |
| + | * New member joined: Sereysethy Touch: Teaching Assistant in Faculty of Computer Science at University of Namur, Belgium. | ||
| + | * Second meeting held (Talal, Prabhant and Sethy) | ||
| − | + | February 2018: <br /> | |
| + | * First meeting held (Talal, Jean- Noël and Prabhant) | ||
| + | * Project content to be updated on google docs until we come up with the first draft, then it will be available on the wiki and github pages. | ||
| − | * | + | January 2018:<br /> |
| + | 2 members joined the team: | ||
| + | * Jean-Noël Colin: Professor in CS Faculty of University of Namur, Belgium, working in the broad field of information security, and more recently, looking at using ML methods for security purposes | ||
| + | * Prabhant Singh: Master student at University of Tartu, currently researching on secure and reliable machine learning. have been associated with owasp from last 2 years. | ||
| − | < | + | September 2017:<br /> |
| − | + | * Project introduction in webinar (attached) | |
| + | [[File:https://www.owasp.org/images/c/cc/Machine_Learning_for_Application_Security_Professionals.pdf|thumb]] | ||
== Quick Download == | == Quick Download == | ||
TBD | TBD | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
==Classifications== | ==Classifications== | ||
{| width="200" cellpadding="2" | {| width="200" cellpadding="2" | ||
|- | |- | ||
| − | | rowspan="2" | + | | rowspan="2" width="50%" valign="top" align="center" | [[File:New projects.png|100px|link=https://www.owasp.org/index.php/OWASP_Project_Stages#tab=Incubator_Projects]] |
| − | | | + | | width="50%" valign="top" align="center" | [[File:Owasp-builders-small.png|link=]] |
|- | |- | ||
| − | | | + | | width="50%" valign="top" align="center" | [[File:Owasp-defenders-small.png|link=]] |
|- | |- | ||
| colspan="2" align="center" | [[File:Cc-button-y-sa-small.png|link=http://creativecommons.org/licenses/by-sa/3.0/]] | | colspan="2" align="center" | [[File:Cc-button-y-sa-small.png|link=http://creativecommons.org/licenses/by-sa/3.0/]] | ||
| Line 75: | Line 69: | ||
==How can I participate in your project?== | ==How can I participate in your project?== | ||
| − | + | This project requires a lot of participations from data scientists, ML experts, software developers, risk managers and application security specialists. Please make the Project Leader's aware of your available time to contribute to the project. It is also important to let the Leader's know how you would like to contribute and pitch in to help the project meet it's goals and milestones. There are many different ways you can contribute to an OWASP Project, but communication with the leads is key. | |
| − | |||
| − | |||
| − | |||
= Acknowledgements = | = Acknowledgements = | ||
==Contributors== | ==Contributors== | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
The success of OWASP is due to a community of enthusiasts and contributors that work to make our projects great. The first contributors to the project were: | The success of OWASP is due to a community of enthusiasts and contributors that work to make our projects great. The first contributors to the project were: | ||
| − | * [[User:Talal Albacha]] | + | * Project Leader: [[User:Talal Albacha|Talal Albacha]] |
| − | * | + | * Project Co-leader : [[User: Sdeleersnyder|Sebastien Deleersnyder]] |
| + | * [Https://www.linkedin.com/in/jncolin/|Prof. Jean-Noël Colin] | ||
| + | * [Https://twitter.com/prabhantsingh Prabhant Singh] | ||
| + | * Sereysethy Touch | ||
| + | * ..[your name].. | ||
= Road Map and Getting Involved = | = Road Map and Getting Involved = | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
We will have ANNUAL release of the up-to-date top 5 risks, organized as following: | We will have ANNUAL release of the up-to-date top 5 risks, organized as following: | ||
| − | * Draft version | + | * Draft version (https://github.com/OWASP/Top-5-Machine-Learning-Risks/) |
* Community responses | * Community responses | ||
* Validate in AppSec conference | * Validate in AppSec conference | ||
* Release final list for the year. | * Release final list for the year. | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
__NOTOC__ <headertabs></headertabs> | __NOTOC__ <headertabs></headertabs> | ||
Latest revision as of 19:50, 28 August 2018
The OWASP Top 5 Machine Learning RisksThe idea is to build the required resources which help software security community to understand the emerging technology of machine learning and how it is related to security, warn them about the risk associated with using ML, and discuss the defending techniques. DescriptionMachine Learning has recently re-emerged as a powerful tool in multiple business sectors. It also becomes vital when it is harnessed for the Security services and applications like Fraud Detection, Anomaly Detection, Behavioral Analysis, etc. Although these applications have huge success, there are still security risks associated with the learning technique especially the security of the learning phase; which can still be vulnerable to threats originated by potential adversaries, and consequently it has considerable impact on their prediction results This project will list these risks and the defending techniques LicensingThe OWASP Top 5 Machine Learning Risks project is licensed under the http://creativecommons.org/licenses/by-sa/3.0/ Creative Commons Attribution-ShareAlike 3.0 license], so you can copy, distribute and transmit the work, and you can adapt it, and use it commercially, but all provided that you attribute the work and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same or similar license to this one. |
Project NewsJune 2018:
February 2018:
January 2018:
September 2017:
Quick DownloadTBD Classifications
| |||||||
How can I participate in your project?
This project requires a lot of participations from data scientists, ML experts, software developers, risk managers and application security specialists. Please make the Project Leader's aware of your available time to contribute to the project. It is also important to let the Leader's know how you would like to contribute and pitch in to help the project meet it's goals and milestones. There are many different ways you can contribute to an OWASP Project, but communication with the leads is key.
Contributors
The success of OWASP is due to a community of enthusiasts and contributors that work to make our projects great. The first contributors to the project were:
- Project Leader: Talal Albacha
- Project Co-leader : Sebastien Deleersnyder
- Jean-Noël Colin
- Prabhant Singh
- Sereysethy Touch
- ..[your name]..
We will have ANNUAL release of the up-to-date top 5 risks, organized as following:
- Draft version (https://github.com/OWASP/Top-5-Machine-Learning-Risks/)
- Community responses
- Validate in AppSec conference
- Release final list for the year.
