Risk area 5: Human-Computer Interaction Harms

Record summary

A quick snapshot of what this page covers.

Techniques3Attack methods connected to this risk.

Mitigations0Defenses that may help with related attacks.

Domain5. Human-Computer InteractionThe broad risk area this belongs to.

Risk profile

How this risk is described and categorized.

"This section focuses on risks specifically from LM applications that engage a user via dialogue, also referred to as conversational agents (CAs) [142]. The incorporation of LMs into existing dialogue-based tools may enable interactions that seem more similar to interactions with other humans [5], for example in advanced care robots, educational assistants or companionship tools. Such interaction can lead to unsafe use due to users overestimating the model, and may create new avenues to exploit and violate the privacy of the user. Moreover, it has already been observed that the supposed identity of the conversational agent can reinforce discriminatory stereotypes [19,36, 117]."

Domain5. Human-Computer Interaction

Subdomain5.1 > Overreliance and unsafe use

Entity3 - Other

Intent3 - Other

Timing2 - Post-deployment

CategoryRisk area 5: Human-Computer Interaction Harms

Subcategoryn/a

Related techniques

Attack methods connected to this risk.

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.

Included resource

Taxonomy of Risks posed by Language Models

AuthorsWeidinger et al.Year2022TypeConference Paper

DOI10.1145/3531146.3533088 URLhttps://doi.org/10.1145/3531146.3533088

Original source

MIT AI Risk Repository

Open the public repository used for AI risk records and taxonomy fields.

Repositoryhttps://airisk.mit.edu/