В LLM можно внедрить спящего агента (https://fxtwitter.com/AnthropicAI/status/1745854907968880970). Триггером для него станет определенная фраза, после которой агент начнет менять поведение этой модели, на картинке показано как. На данный момент это один из самых интересных секьюрити-кейсов, связанных с LLM
Мне вспоминается концепция троянского обучения в педагогике - ОНО. Ваш виртуальный помощник на каком-то этапе начинающий советовать совершать критические ошибки
В LLM можно внедрить спящего агента (https://fxtwitter.com/AnthropicAI/status/1745854907968880970). Триггером для него станет определенная фраза, после которой агент начнет менять поведение этой модели, на картинке показано как. На данный момент это один из самых интересных секьюрити-кейсов, связанных с LLM
Мне вспоминается концепция троянского обучения в педагогике - ОНО. Ваш виртуальный помощник на каком-то этапе начинающий советовать совершать критические ошибки
Given the pro-privacy stance of the platform, it’s taken as a given that it’ll be used for a number of reasons, not all of them good. And Telegram has been attached to a fair few scandals related to terrorism, sexual exploitation and crime. Back in 2015, Vox described Telegram as “ISIS’ app of choice,” saying that the platform’s real use is the ability to use channels to distribute material to large groups at once. Telegram has acted to remove public channels affiliated with terrorism, but Pavel Durov reiterated that he had no business snooping on private conversations. This ability to mix the public and the private, as well as the ability to use bots to engage with users has proved to be problematic. In early 2021, a database selling phone numbers pulled from Facebook was selling numbers for $20 per lookup. Similarly, security researchers found a network of deepfake bots on the platform that were generating images of people submitted by users to create non-consensual imagery, some of which involved children. The SC urges the public to refer to the SC’s I nvestor Alert List before investing. The list contains details of unauthorised websites, investment products, companies and individuals. Members of the public who suspect that they have been approached by unauthorised firms or individuals offering schemes that promise unrealistic returns Such instructions could actually endanger people — citizens receive air strike warnings via smartphone alerts. Asked about its stance on disinformation, Telegram spokesperson Remi Vaughn told AFP: "As noted by our CEO, the sheer volume of information being shared on channels makes it extremely difficult to verify, so it's important that users double-check what they read."
from jp
