Backdoor Attacks

From Cognitive Attack Taxonomy
Revision as of 02:54, 30 July 2024 by EE (talk | contribs) (Created page with "== '''Backdoor Attacks ''' == '''Short Description:''' The attacker surreptitiously changes the training data by adding examples with maliciously crafted cues. <br> '''CAT ID:''' CAT-2023-009 <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 Co...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Backdoor Attacks

Short Description: The attacker surreptitiously changes the training data by adding examples with maliciously crafted cues.

CAT ID: CAT-2023-009

Layer: 7

Operational Scale: Operational

Level of Maturity: Proof of Concept

Category: TTP

Subcategory:

Also Known As:

Description:

Brief Description:

Closely Related Concepts:

Mechanism:

Multipliers:

Detailed Description: The attacker surreptitiously changes the training data set adding examples with specially crafted cues designed to cause the model to misbehave upon encountering the specific cues.

INTERACTIONS [VETs]:

Examples:

Use Case Example(s):

Example(s) From The Wild:

Comments:

References: