F-Secure Researchers Publish Taxonomy of 26 Consumer AI Harms
Start here
F-Secure's Illuminate Research team has published a taxonomy of 26 ways AI can harm consumers, organized by five relationship types: chatbot to consumer, agent to consumer, threat actor to consumer, threat actor to agent, and threat actor to chatbot. Each harm is traced through 19 intermediary layers, including foundation models, agent runtimes, memory stores and consumer devices, so that defenses can be placed where they would actually need to be built. The authors say many of these harms can only be fixed by the companies that make the models and run the products, and they describe the taxonomy as still a work in progress.
Generated from reports · updated 4 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AITaxonomy of 26 Ways AI Can Make Your Life Worse
A new taxonomy maps 26 consumer AI harms across five relationship types — chatbot → consumer, agent → consumer, threat actor → consumer, threat actor → agent, and threat actor → chatbot. Each harm is traced through 19 intermediary layers, such as foundation models, agent runtimes, memory stores and consumer devices, so defenses attach where they would actually have to be built. The authors note many harms can only be fixed by the companies making the models and running the products, and that the work is still in progress.
Heat for this event
Not enough continuous observations yet to draw a trend.