# Protecting people from harmful manipulation

DevFeed: [Protecting people from harmful manipulation](<https://devfeed.tech/articles/protecting-people-from-harmful-manipulation-6235.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/protecting-people-from-harmful-manipulation/>)

Author: Helen King

Published: 2026-03-25T16:46:20Z

Content type: article

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Google](<https://devfeed.tech/topics/google.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [finance](<https://devfeed.tech/tags/finance.md>), [health](<https://devfeed.tech/tags/health.md>), [india](<https://devfeed.tech/tags/india.md>), [research](<https://devfeed.tech/tags/research.md>), [responsibility-safety](<https://devfeed.tech/tags/responsibility-safety.md>), [safety](<https://devfeed.tech/tags/safety.md>), [testing](<https://devfeed.tech/tags/testing.md>), [uk](<https://devfeed.tech/tags/uk.md>), [us](<https://devfeed.tech/tags/us.md>)

## AI overview

Google DeepMind presents research on the risk of AI systems being misused for harmful manipulation: using emotional and cognitive vulnerabilities to influence people toward harmful choices. The work introduces an empirically validated toolkit and evaluation framework, with materials for human participant studies, based on nine controlled studies involving more than 10,000 participants in the UK, US, and India.

## Source excerpt

Google DeepMind researches AI's harmful manipulation risks across areas like finance and health, leading to new safety measures.