APromptRiskDBThreat intelligence atlas
AI Security Technique

Machine Compromise - AI Security Technique

Adversaries may compromise a machine by exploiting or manipulating AI-enabled components on the system. Compromising a victim system allows the adversary to execute arbitrary code, steal credentials, exfiltrate data, and continue to persist on the system. Adversaries may target a Local AI Agent which if compromised grants them the capabilities and permissions of the agent, or [AI Artif...

View mitigationsRead context
AI Security TechniquedemonstratedImpact

Record summary

A quick snapshot of what this page covers.

Tactics1Attacker goals connected to this method.
Mitigations0Defenses that may help against this attack.
AI risks5Research-backed risks connected to this topic.

Attack context

How this AI attack works in practice.

Adversaries may compromise a machine by exploiting or manipulating AI-enabled components on the system. Compromising a victim system allows the adversary to execute arbitrary code, steal credentials, exfiltrate data, and continue to persist on the system.

Adversaries may target a Local AI Agent which if compromised grants them the capabilities and permissions of the agent, or AI Artifacts which can contain embedded malware.

ATLAS ID
AML.T0112
Priority score
45
Maturity: demonstrated
Impact

Mitigations

Defenses that may help against this attack.

No connected defenses. No defense is connected to this attack in the current data.

Case studies

Examples from public reports and exercises.

No case studies found. No public example is connected to this attack in the current data.

Related risks

Research-backed risks connected to this topic.

Adversarial AI: Data and Model Exfiltration Attacks

Confidence: 0.67
Domain2. Privacy & SecuritySubdomain2.1 > Compromise of privacy by leaking or correctly inferring sensitive information

"Other forms of abuse can include privacy attacks that allow adversaries to exfiltrate or gain knowledge of the private training data set or other valuable assets. For example, privacy attacks such as membership infer...

Jailbreak of a multimodal model

Confidence: 0.67
Domain2. Privacy & SecuritySubdomain2.2 > AI system security vulnerabilities and attacks

"Current generation multimodal (e.g., vision and language) GPAI models are vulnerable to adversarial jailbreak attacks. These attacks can be used to automatically induce a model to produce an arbitrary or specific out...

Model extraction

Confidence: 0.67
Domain2. Privacy & SecuritySubdomain2.2 > AI system security vulnerabilities and attacks

"Data Exfiltration goes beyond revealing private information, and involves illicitly obtaining the training data used to build a model that may be sensitive or proprietary. Model Extraction is the same attack, only di...

Data exfiltration

Confidence: 0.67
Domain2. Privacy & SecuritySubdomain2.2 > AI system security vulnerabilities and attacks

"Data Exfiltration goes beyond revealing private information, and involves illicitly obtaining the training data used to build a model that may be sensitive or proprietary. Model Extraction is the same attack, only di...

Attacking LLMs via Additional Modalities a

Confidence: 0.65
Domain2. Privacy & SecuritySubdomain2.2 > AI system security vulnerabilities and attacks

"LLMs can now process modalities other than text, e.g. images or video frames (OpenAI, 2023c; Gemini Team, 2023). Several studies show that gradient-based attacks on multimodal models are easy and effective (Carlini e...

Related CVEs

Known software flaws linked to this context.

No related CVEs. No software flaw is connected to this attack in the current data.

Source

Where this page information comes from.