PromptRiskDBThreat intelligence atlas
AI Risk

Domain-Specific Misuses

"Improvements in LLMs may exert greater pressure to apply LLMs to various domains, such as health and education (Eloundou et al., 2023). Crude efforts to use LLMs in such domains, however, may incur harm and should be discouraged strongly. In particular, it is important to guard against different ways in which LLMs may be misused within any domain. One famous episode of misuse within the health sector is a mental...

AI Risk4. Malicious Actors & Misuse4.3 > Fraud, scams, and targeted manipulation2 - Post-deployment

Record summary

A quick snapshot of what this page covers.

Techniques1Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Domain4. Malicious Actors & MisuseThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

"Improvements in LLMs may exert greater pressure to apply LLMs to various domains, such as health and education (Eloundou et al., 2023). Crude efforts to use LLMs in such domains, however, may incur harm and should be discouraged strongly. In particular, it is important to guard against different ways in which LLMs may be misused within any domain. One famous episode of misuse within the health sector is a mental health non-profit experimenting LLM-based therapy on its users without their informed consent (Xiang, 2023a). Within the education sector, LLMs may be misused in various ways that might impact student learning; e.g. as cheating accessory by the students or as (low quality) evaluator of student’s work by the instructors (Cotton et al., 2023). Recent findings in moral psychology also suggest that LLMs can generate moral evaluations that people perceive as superior to human judgments; these could be misused to create compelling yet harmful moral guidance (Aharoni et al., 2024). Similar risks of misuse may exist in other domains as well."

Domain4. Malicious Actors & Misuse
Subdomain4.3 > Fraud, scams, and targeted manipulation
Entity1 - Human
Intent1 - Intentional
Timing2 - Post-deployment
CategoryDual-Use Capabilities Enable Malicious Use and Misuse of LLMs
SubcategoryDomain-Specific Misuses

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.