Researchers at Google\u2019s Threat Intelligence Group (GTIG) have discovered that hackers are creating malware that can harness the power of large language models (LLMs) to rewrite itself on the fly.<\/p>\n
An experimental malware family dubbed PROMPTFLUX, identified by GTIG in a recent blog post<\/a>, can rewrite its own code to avoid detection.<\/p>\n It\u2019s an escalation that could make future malware far more difficult to detect, further highlighting growing cybersecurity concerns<\/a> brought on by the advent and widespread adoption of generative AI.<\/p>\n Tools like PROMPTFLUX \u201cdynamically generate malicious scripts, obfuscate their own code to evade detection, and leverage AI models to create malicious functions on demand, rather than hard-coding them into the malware,\u201d GTIG wrote.<\/p>\n According to the tech giant, this new \u201cjust-in-time\u201d approach \u201crepresents a significant step toward more autonomous and adaptive malware.\u201d<\/p>\n PROMPTFLUX is a Trojan horse malware that interacts with Google\u2019s Gemini AI model\u2019s application programming interface (API) to learn how to modify itself to avoid detection on the fly.<\/p>\n \u201cFurther examination of PROMPTFLUX samples suggests this code family is currently in a development or testing phase since some incomplete features are commented out and a mechanism exists to limit the malware\u2019s Gemini API calls,\u201d the group wrote.<\/p>\n Fortunately, the exploit has yet to be observed infecting machines in the wild, as the \u201ccurrent state of this malware does not demonstrate an ability to compromise a victim network or device,\u201d Google noted. \u201cWe have taken action to disable the assets associated with this activity.\u201d<\/p>\n Nonetheless, GTIG noted that malware like PROMPTFLUX appears to be \u201cassociated with financially motivated actors.\u201d The team warned of a maturing \u201cunderground marketplace for illicit AI tools,\u201d which could lower the \u201cbarrier to entry for less sophisticated actors.\u201d<\/p>\n The threat of adversaries leveraging AI tools is very real. According to Google, \u201cState-sponsored actors from North Korea, Iran, and the People\u2019s Republic of China\u201d are already tinkering with the AI to enhance their operations.<\/p>\n In response to the threat, GTIG introduced a new conceptual framework aimed at securing AI systems.<\/p>\n While generative AI can be used to create almost impossible-to-detect malware, it can be used for good as well. For instance, Google recently introduced an AI agent, dubbed Big Sleep<\/a>, which is designed to use AI to identify security vulnerabilities in software.<\/p>\n In other words, it\u2019s AI being pitted against AI in a cybersecurity war that\u2019s evolving rapidly.<\/p>\n