As if AI weren’t enough of a security concern, now researchers have discovered that open-source AI deployments may be an even bigger problem than those from commercial providers.
Threat researchers at SentinelLABS teamed up with internet mappers from Censys to take a look at the footprint of Ollama deployments exposed to the internet, and what they found was a global network of largely homogenous, open-source AI deployments just waiting for the right zero-day to come along.
175,108 unique Ollama hosts in 130 countries were found exposed to the public internet, with the vast majority of instances found to be running Llama, Qwen2, and Gemma2 models, most of those relying on the same compression choices and packaging regimes. That, says the pair, suggests open-source AI deployments have become a monoculture ripe for exploitation.
Ollama with standard Gemma2 model open to the Internet. What could go wrong?
I call out this one because the Chinese government has already examined it for exploits and flaws.
Letting it run outside a sandbox on the Internet is tantamount to sharing any information and capabilities it has with the CCP.
Or any number of malfeasants.