![\"ChatGPT](\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/07\/study-exposes-security.jpg\")
<\/p>\nHow GhostWriter targets AI’s long-term memory<\/p>\n
The researchers explain that modern personal AI agents combine the capabilities of a conversational chatbot with task execution, such as sending messages, scheduling meetings, or editing code.<\/p>\n
When these systems interact with untrusted information sources, they become vulnerable to memory poisoning attacks.<\/p>\n
In their paper, researchers George Torres, Sharad Shrestha, and Satyajayant Misra describe how GhostWriter works. The technique involves planting false memories or hidden instructions inside an AI model’s long-term memory.<\/p>\n
The attack consists of two stages:<\/p>\n
Injection: The attacker secretly inserts a malicious payload into the target AI agent. <\/p>\n
Activation: The poisoned memory is later retrieved from storage when the AI processes a legitimate user request. <\/p>\n
One example described by the researchers involves an AI assistant that manages email. The attacker implants a hidden instruction telling the model to regularly summarize emails from banks or financial institutions and secretly forward those summaries to the attacker’s email address.<\/p>\n
Experiments showed that GhostWriter achieved an injection success rate of nearly 98% and an average activation rate of about 60% against modern AI agents.<\/p>\n
<\/p>\n
LLM agents without memory process every interaction in isolation. LLM agents with persistent memory can store information and retrieve it later when needed (Illustration: George Torres, Sharad Shrestha, and Satyajayant Misra)<\/p>\n
\n
\nHow can the threat be stopped?
\n
<\/p>\n
According to the researchers, the vulnerability exists because AI systems lack security-focused memory management. To address the issue, they developed a defense system called Agentic Memory Sentry (AM-Sentry).<\/p>\n
\n
<\/p>\n
AM-Sentry relies on two key mechanisms:<\/p>\n
\n
<\/p>\n
Memory-saving policy: Controls how new information is written to long-term memory. <\/p>\n
Memory-retrieval screen: Checks stored instructions immediately before they are retrieved and executed. <\/p>\n
According to the team’s experiments, AM-Sentry significantly reduces the success rate of GhostWriter attacks while preserving the AI agent’s overall functionality and performance.<\/p>\n
\n
<\/p>\n
The researchers believe that these protection strategies could be adapted to improve the security of other AI systems with long-term memory.<\/p>\n
\n
\n
<\/p>\n","protected":false},"excerpt":{"rendered":"How GhostWriter targets AI’s long-term memory The researchers explain that modern personal AI agents combine the capabilities of…\n","protected":false},"author":2,"featured_media":114764,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[24,580,157,12602,134],"class_list":["post-114763","post","type-post","status-publish","format-standard","has-post-thumbnail","category-openai","tag-ai","tag-chatgpt","tag-openai","tag-scientist","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/114763","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=114763"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/114763\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/114764"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=114763"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=114763"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=114763"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}