APromptRiskDBThreat intelligence atlas
AI Security Technique

Physical Environment Access - AI Security Technique

In addition to the attacks that take place purely in the digital domain, adversaries may also exploit the physical environment for their attacks. If the model is interacting with data collected from the real world in some way, the adversary can influence the model through access to wherever the data is being collected. By modifying the data in the collection process, the adversary can perform modified versions of...

AI Security TechniquedemonstratedAI Model Access

Record summary

A quick snapshot of what this page covers.

Tactics1Attacker goals connected to this method.
Mitigations1Defenses that may help against this attack.
AI risks0Research-backed risks connected to this topic.

Attack context

How this AI attack works in practice.

In addition to the attacks that take place purely in the digital domain, adversaries may also exploit the physical environment for their attacks. If the model is interacting with data collected from the real world in some way, the adversary can influence the model through access to wherever the data is being collected. By modifying the data in the collection process, the adversary can perform modified versions of attacks designed for digital access.

ATLAS ID
AML.T0041
Priority score
43
Maturity: demonstrated
AI Model Access

Mitigations

Defenses that may help against this attack.

AML.M0009 - Use Multi-Modal Sensors

Business and Data UnderstandingData Preparation+1 more
LifecycleBusiness and Data Understanding + 2 moreCategoryTechnical - Cyber

Using a variety of sensors can make it more difficult for an attacker with physical access to compromise and produce malicious results.

Case studies

Examples from public reports and exercises.

Backdoor Attack on Deep Learning Models in Mobile Apps

exercise
Date2021-01-18

Deep learning models are increasingly used in mobile applications as critical components. Researchers from Microsoft Research demonstrated that many deep learning models deployed in mobile apps are vulnerable to backdoor attacks via "neural payload injection." They conducted an empirical study on real-world mobile deep learning apps collected from Google Play. They identified 54 apps that were vulnerable to attack, including popular security and safety critical applications used for cash recognition, parental control, face authentication, and financial services.

Face Identification System Evasion via Physical Countermeasures

exercise
Date2020-01-01

MITRE's AI Red Team demonstrated a physical-domain evasion attack on a commercial face identification service with the intention of inducing a targeted misclassification. This operation had a combination of traditional MITRE ATT&CK techniques such as finding valid accounts and executing code via an API - all interleaved with adversarial ML specific attacks.

Source

Where this page information comes from.