https://cognitiveattacktaxonomy.org/index.php?action=history&feed=atom&title=Training_Data_Poisoning_Attack Training Data Poisoning Attack - Revision history 2026-04-19T08:22:21Z Revision history for this page on the wiki MediaWiki 1.42.1 https://cognitiveattacktaxonomy.org/index.php?title=Training_Data_Poisoning_Attack&diff=209&oldid=prev EE: Created page with "== '''Training Data Poisoning Attack ''' == '''Short Description:''' An attacker changes training data to manipulate the model to act favorably for the attacker. <br> '''CAT ID:''' CAT-2023-007 <br> '''Layer:''' 7 <br> '''Operational Scale:''' Operational <br> '''Level of Maturity:''' Proof of Concept <br> '''Category:''' TTP <br> '''Subcategory:''' <br> '''Also Known As:''' <br> == '''Description:''' == '''Brief Description:''' <br> '''Closely Related..." 2024-07-30T02:56:01Z <p>Created page with &quot;== &#039;&#039;&#039;Training Data Poisoning Attack &#039;&#039;&#039; == &#039;&#039;&#039;Short Description:&#039;&#039;&#039; An attacker changes training data to manipulate the model to act favorably for the attacker. &lt;br&gt; &#039;&#039;&#039;CAT ID:&#039;&#039;&#039; CAT-2023-007 &lt;br&gt; &#039;&#039;&#039;Layer:&#039;&#039;&#039; 7 &lt;br&gt; &#039;&#039;&#039;Operational Scale:&#039;&#039;&#039; Operational &lt;br&gt; &#039;&#039;&#039;Level of Maturity:&#039;&#039;&#039; Proof of Concept &lt;br&gt; &#039;&#039;&#039;Category:&#039;&#039;&#039; TTP &lt;br&gt; &#039;&#039;&#039;Subcategory:&#039;&#039;&#039; &lt;br&gt; &#039;&#039;&#039;Also Known As:&#039;&#039;&#039; &lt;br&gt; == &#039;&#039;&#039;Description:&#039;&#039;&#039; == &#039;&#039;&#039;Brief Description:&#039;&#039;&#039; &lt;br&gt; &#039;&#039;&#039;Closely Related...&quot;</p> <p><b>New page</b></p><div>== &#039;&#039;&#039;Training Data Poisoning Attack &#039;&#039;&#039; ==<br /> <br /> &#039;&#039;&#039;Short Description:&#039;&#039;&#039; An attacker changes training data to manipulate the model to act favorably for the attacker. &lt;br&gt;<br /> <br /> &#039;&#039;&#039;CAT ID:&#039;&#039;&#039; CAT-2023-007 &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Layer:&#039;&#039;&#039; 7 &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Operational Scale:&#039;&#039;&#039; Operational &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Level of Maturity:&#039;&#039;&#039; Proof of Concept &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Category:&#039;&#039;&#039; TTP &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Subcategory:&#039;&#039;&#039; &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Also Known As:&#039;&#039;&#039; &lt;br&gt;<br /> <br /> == &#039;&#039;&#039;Description:&#039;&#039;&#039; ==<br /> <br /> &#039;&#039;&#039;Brief Description:&#039;&#039;&#039; &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Closely Related Concepts:&#039;&#039;&#039; &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Mechanism:&#039;&#039;&#039; &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Multipliers:&#039;&#039;&#039; &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Detailed Description:&#039;&#039;&#039; An attacker changes training data (or data labels) to manipulate the model to act favorably for the attacker. Can be insideous because the model appears to function normally but reacts unexpectedly when encountering a specific condition. &lt;br&gt;<br /> <br /> &#039;&#039;&#039;INTERACTIONS&#039;&#039;&#039; [VETs]: &lt;br&gt;<br /> <br /> == &#039;&#039;&#039;Examples:&#039;&#039;&#039; ==<br /> <br /> &#039;&#039;&#039;Use Case Example(s):&#039;&#039;&#039; &lt;br&gt;<br /> <br /> &#039;&#039;&#039;Example(s) From The Wild:&#039;&#039;&#039; &lt;br&gt;<br /> <br /> == &#039;&#039;&#039;Comments:&#039;&#039;&#039; ==<br /> <br /> == &#039;&#039;&#039;References:&#039;&#039;&#039; ==</div> EE