Thanks for alerting to this. I feel this is not discussed enough in the media, all anyone talks about is how wonderful AI is for productivity etc
Quote from the article:
The research methodology involved embedding written instructions within computer programs rather than traditional pre-written attack code. When activated, the malware contacts AI language models to generate Lua scripts customized for each victim's specific computer setup, using open-source models that lack the safety restrictions of commercial AI services.
Each execution produces unique attack code despite identical starting prompts, creating a major challenge for cybersecurity defenses. Traditional security software relies on detecting known malware signatures or behavioral patterns, but AI-generated attacks produce variable code and execution behaviors that could evade these detection systems entirely.
Testing across three representative environments showed both AI models were highly effective at system mapping and correctly flagged 63-96% of sensitive files depending on environment type. The AI-generated scripts proved cross-platform compatible, operating on (desktop/server) Windows, Linux, and (embedded) Raspberry Pi systems without modification.
Thanks for alerting to this. I feel this is not discussed enough in the media, all anyone talks about is how wonderful AI is for productivity etc
Quote from the article:
The research methodology involved embedding written instructions within computer programs rather than traditional pre-written attack code. When activated, the malware contacts AI language models to generate Lua scripts customized for each victim's specific computer setup, using open-source models that lack the safety restrictions of commercial AI services.
Each execution produces unique attack code despite identical starting prompts, creating a major challenge for cybersecurity defenses. Traditional security software relies on detecting known malware signatures or behavioral patterns, but AI-generated attacks produce variable code and execution behaviors that could evade these detection systems entirely.
Testing across three representative environments showed both AI models were highly effective at system mapping and correctly flagged 63-96% of sensitive files depending on environment type. The AI-generated scripts proved cross-platform compatible, operating on (desktop/server) Windows, Linux, and (embedded) Raspberry Pi systems without modification.
/quote