PromptRiskDBThreat intelligence atlas
AI Risk

Encoded reasoning

"Models can employ steganography techniques to encode their intermediate rea- soning steps in ways that are not interpretable by humans [166]. Since en- coded reasoning can improve model performance, this tendency might naturally emerge and become more pronounced with more capable models."

View related techniquesRead profile
AI Risk7. AI System Safety, Failures, & Limitations7.2 > AI possessing dangerous capabilities2 - Post-deployment

Record summary

A quick snapshot of what this page covers.

Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain7. AI System Safety, Failures, & LimitationsThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

Domain7. AI System Safety, Failures, & Limitations
Subdomain7.2 > AI possessing dangerous capabilities
Entity2 - AI
Intent1 - Intentional
Timing2 - Post-deployment
CategoryModel Evaluations (Interpretability/Explainability)
SubcategoryEncoded reasoning

Related techniques

Attack methods connected to this risk.

No linked attack methods. No AI attack method is connected to this risk in the current data.

Suggested mitigations

Defenses that may help with related attacks.

No propagated mitigations. No defense is available through the connected attack methods.

Source

Research source for this risk, when available.