Self-replicating Morris II worm targets AI email assistants

[Caute_cautim]

Hi All

The proliferation of generative artificial intelligence (gen AI) email assistants such as OpenAI’s GPT-3 and Google’s Smart Compose has revolutionized communication workflows. Unfortunately, it has also introduced novel attack vectors for cyber criminals.

Leveraging recent advancements in AI and natural language processing, malicious actors can exploit vulnerabilities in gen AI systems to orchestrate sophisticated cyberattacks with far-reaching consequences. Recent studies have uncovered the insidious capabilities of self-replicating malware, exemplified by the “Morris II” strain created by researchers.

https://securityintelligence.com/posts/morris-ii-self-replicating-malware-genai-email-assistants/

Regards

Caute_Cautim

[Until_then]

Pretty interesting. I haven't been a fan of AI because of the increased risk. I wonder, though, what kind of benefits outweigh these risks? I have limited experience in AI and don't know all of what it has to offer in our current society. 

[Caute_cautim]

@Until_thenI would not be put off by the bad press - there are organisations who from the outset set out a entire set of Governance and ethics from end to end at the outset of their AI journey, there are guard rails built into their models, which are thoroughly tested and verified via a Privacy and Governance board prior to being released for general usage. 

Unfortunately ChatGPT, and others as usual did not think through the ramifications of their releases. Yes, it generated a great deal of media and interest, experimentation but also the bad actors saw the opportunities to exploit it as well - which they are doing very nicely thank you.

There are plenty of examples of Microsoft Co-pilot deciding to take a "God" like entity and other bad impressions, they have since cleaned up their act - but really this sort of thing should not have taken place, if they were really responsible for how society would react and realise the impressions on young people's minds, or giving the impression that all input was true and all output was entirely true - but as we know in life, this rarely happens. 

Regards

Caute_Cautim