Forums
New posts
Search forums
News
Security News
Technology News
Giveaways
Giveaways, Promotions and Contests
Discounts & Deals
Reviews
Users Reviews
Video Reviews
Support
Windows Malware Removal Help & Support
Inactive Support Threads
Mac Malware Removal Help & Support
Mobile Malware Removal Help & Support
Blog
Log in
Register
What's new
Search
Search titles only
By:
Search titles only
By:
Reply to thread
Menu
Install the app
Install
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Forums
Security
Security Statistics and Reports
Randomness in the AV Labs testing.
Message
<blockquote data-quote="Andy Ful" data-source="post: 1123466" data-attributes="member: 32260"><p><strong><span style="font-size: 18px">AVLab example.</span></strong></p><p>(Post corrected)</p><p></p><p>AVLab 2023-2024 + January, March 2025</p><p>Number of samples in all tests: 607+759+958+510+275+521+459+380+245+343+468+416+567+447 = 6955</p><p></p><p>Number of samples tested by Avast + Bitdefender + F-Secure:</p><p>3*6955 - (510+380+245+468+416+447) = 18399</p><p>Kaspersky was skipped due to an insufficient number of tests.</p><p></p><p>Number of samples missed by Avast + Bitdefender + F-Secure:</p><p>1+1+1+1+5+5+4+13 = 31</p><p></p><p>Average infection rate of top AVs</p><p>r = 31/18399 ~ 1/600</p><p></p><p>[ATTACH=full]288200[/ATTACH]</p><p></p><p>Threshold criteria:</p><p>p(t) = 0.05 for r = 1/600</p><p></p><p>2 missed per 400 samples gives the 99.5% threshold for passed samples.</p><p>2 missed per 500 samples gives the 99.6% threshold for passed samples.</p><p>3 missed per 600 samples gives the 99.5% threshold for passed samples.</p><p>3 missed per 800 samples gives the 99.6% threshold for passed samples.</p><p></p><p>If the number of samples is 400-800, then the fixed threshold for passed samples is about 99.5%.</p><p>Currently, AVLab uses the fixed threshold of 99% for passed samples, which seems too low.</p><p></p><p>Edit 1.</p><p>Corrected a typo error in the formula for p(x).</p><p></p><p>Edit 2.</p><p>Corrected missed samples for F-Secure and Bitdefender, and the data based on the corrected infection rate.</p></blockquote><p></p>
[QUOTE="Andy Ful, post: 1123466, member: 32260"] [B][SIZE=5]AVLab example.[/SIZE][/B] (Post corrected) AVLab 2023-2024 + January, March 2025 Number of samples in all tests: 607+759+958+510+275+521+459+380+245+343+468+416+567+447 = 6955 Number of samples tested by Avast + Bitdefender + F-Secure: 3*6955 - (510+380+245+468+416+447) = 18399 Kaspersky was skipped due to an insufficient number of tests. Number of samples missed by Avast + Bitdefender + F-Secure: 1+1+1+1+5+5+4+13 = 31 Average infection rate of top AVs r = 31/18399 ~ 1/600 [ATTACH type="full" width="254px" alt="1745315505062.png"]288200[/ATTACH] Threshold criteria: p(t) = 0.05 for r = 1/600 2 missed per 400 samples gives the 99.5% threshold for passed samples. 2 missed per 500 samples gives the 99.6% threshold for passed samples. 3 missed per 600 samples gives the 99.5% threshold for passed samples. 3 missed per 800 samples gives the 99.6% threshold for passed samples. If the number of samples is 400-800, then the fixed threshold for passed samples is about 99.5%. Currently, AVLab uses the fixed threshold of 99% for passed samples, which seems too low. Edit 1. Corrected a typo error in the formula for p(x). Edit 2. Corrected missed samples for F-Secure and Bitdefender, and the data based on the corrected infection rate. [/QUOTE]
Insert quotes…
Verification
Post reply
Top
