Git-Mirrors/advmlthreatmatrix
1
0
Fork 0
mirror of https://github.com/mitre/advmlthreatmatrix.git synced 2025-03-13 02:46:29 -04:00
Code Issues Actions Packages Projects Releases Wiki Activity

fixed links

Browse Source
This commit is contained in:
Keith Manville 2020-10-16 13:38:04 -04:00
parent 7a3332a5c9
commit 080b142ffd
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
pages/adversarial-ml-threat-matrix.md
View File

@ -115,7 +115,7 @@ Organizations often grant elevated access to second or third-party external prov
#### ![AdvML](/images/color_advml.png)Execute Unsafe ML Models
An Adversary may utilize unsafe ML Models that when executed have an unintended effect. The adversary can use this technique to establish persistent access to systems. These models may be introduced via a [Pre-Trained Model with Backdoor](#Pre-Trained-Model-with-Backdoor).
An Adversary may utilize unsafe ML Models that when executed have an unintended effect. The adversary can use this technique to establish persistent access to systems. These models may be introduced via a [Pre-Trained Model with Backdoor](#Pre-Trained-ML-Model-with-Backdoor).
> ##### ![AdvML](/images/color_advml.png)ML Models from Compromised Sources
>
@ -137,7 +137,7 @@ Stubs
#### ![AdvML](/images/color_advml.png)Unsafe ML Model Execution
An Adversary may utilize unsafe ML Models that when executed have an unintended effect. The adversary can use this technique to establish persistent access to systems. These models may be introduced via a [Pre-trained Model with Backdoor](#Pre-Trained-Model-with-Backdoor). An example of this technique is to use pickle embedding to introduce malicious data payloads.
An Adversary may utilize unsafe ML Models that when executed have an unintended effect. The adversary can use this technique to establish persistent access to systems. These models may be introduced via a [Pre-trained Model with Backdoor](#Pre-Trained-ML-Model-with-Backdoor). An example of this technique is to use pickle embedding to introduce malicious data payloads.
#### ![Cyber](/images/color_cyber.png)Account Manipulation
@ -168,7 +168,7 @@ Example evasion attacks include Simple Transformation, Common Corruption, Advers
#### ![AdvML](/images/color_advml.png)Model Poisoning
Adversaries can train machine learning that are performant, but contain backdoors that produce inference errors when presented with input containing a trigger defined by the adversary. A model with a backdoor can be introduced by an innocent user via a [pre-trained model with backdoor](#Pre-Trained-Model-with-Backdoor) or can be a result of [Data Poisoning](#Data-Poisoning). This backdoored model can be exploited at inference time with an [Evasion Attack](#Evasion-Attack)
Adversaries can train machine learning that are performant, but contain backdoors that produce inference errors when presented with input containing a trigger defined by the adversary. A model with a backdoor can be introduced by an innocent user via a [pre-trained model with backdoor](#Pre-Trained-ML-Model-with-Backdoor) or can be a result of [Data Poisoning](#Data-Poisoning). This backdoored model can be exploited at inference time with an [Evasion Attack](#Evasion-Attack)
#### ![AdvML](/images/color_advml.png)Data Poisoning