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
General Security Discussions
Adversarial Sample Generation: Making Machine Learning Systems Robust for Security
Message
<blockquote data-quote="ForgottenSeer 58943" data-source="post: 754055"><p>Wow, nice article man. Thanks.</p><p></p><p>I am using several AI/ML systems on my home network now. I've come to the conclusion that against advanced threats and threat actors, it's really the only thing that is going to work. So far, it's worked wonderfully well and has stopped an update channel compromise with a tampered update.</p><p></p><p>Even my gateway has AI/ML systems in place to detect and block anomalies. Testing is going VERY WELL. Last night I did some testing to try and intrude on my network with a local Client-Mode AP hopped off the internal WiFi. The assumption would be the attacker can see my SSID and knows the Passkey, so they create a mirrored station to trick clients into logging into the station mirror which is on a MiTM machine. The AI/ML system picked it up immediately due to some trace anomalies, and blocked it.</p><p></p><p>So far so good but I think this is where we're heading. Static solutions are probably going to become useless at some point.</p></blockquote><p></p>
[QUOTE="ForgottenSeer 58943, post: 754055"] Wow, nice article man. Thanks. I am using several AI/ML systems on my home network now. I've come to the conclusion that against advanced threats and threat actors, it's really the only thing that is going to work. So far, it's worked wonderfully well and has stopped an update channel compromise with a tampered update. Even my gateway has AI/ML systems in place to detect and block anomalies. Testing is going VERY WELL. Last night I did some testing to try and intrude on my network with a local Client-Mode AP hopped off the internal WiFi. The assumption would be the attacker can see my SSID and knows the Passkey, so they create a mirrored station to trick clients into logging into the station mirror which is on a MiTM machine. The AI/ML system picked it up immediately due to some trace anomalies, and blocked it. So far so good but I think this is where we're heading. Static solutions are probably going to become useless at some point. [/QUOTE]
Insert quotes…
Verification
Post reply
Top