#mlsec
17 posts · Last used Sep 17
What happens to recursive pollution in the recursive self-improvement scenario? What is the tipping point between a good attractor and a bad one?
#MLsec
Oh look, a voice of reason in the wilderness! Melanie Mitchell talks about #MLsec and #AI #security from the perspective of a seasoned AI researcher. @melaniemitchell@sigmoid.social
Why does everyone believe that the OpenAI Agentic (hugging face attacking) swarm did not get out of its container? Seriously?
#MLsec
Irregular egg on your face. #MLsechttps://www.irregular.com/research/next-generation-of-cyber-evals
https://www.theinformation.com/articles/meta-ai-model-hacked-another-company-cybersecurity-testing
https://www.wired.com/story/ok-well-there-are-even-more-ai-agent-hacking-incidents/
https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals
Replying to
@cigitalgem@sigmoid.social see what happens when you try to measure #MLsec?!
Autonomy has its...um...benefits? #MLsec
This is the beginning of the beginning.
Is escaping the sandbox new for #AI models? Nope. @roblemos@infosec.exchange provides important background on #AI crime (I am quoted in the story)
#MLsec
Replying to
@volts.wtf what absolute crap.
#MLsec
Recursive pollution for the win... intentionally placed
Replying to
@noplasticshower@infosec.exchange @dennisf@infosec.exchange also note that this identity does most of the #MLsec heavy lifting around here
Replying to
@gleick@mas.to I understand that perspective. Autonomy means autonomy. The company chose to make autonomous things...which by definition don't react well to the control thing.
And this is Agentic AI...a far cry from an LLM. Tool use with RL.
#MLsec
Is this hugging face hack by OpenAI Agentic bots who escaped the lab important?
https://www.nytimes.com/2026/07/21/technology/openai-attack-hugging-face.html
Yes, especially in light of this
https://berryvilleiml.com/2026/06/05/biml-and-the-papernot-worm/
It is both inevitable and very concerning. Autonomy cuts both ways. As the arsenal of sneaky tricks gets bigger, we can expect more interesting exploit chains.
#MLsec #AI
Replying to
@kim_harding@mastodon.scot one of the reasons BIML exists #MLsec
Last night BIML spoke to German TV about the mythos/fable export control situation.
Please help us get this thinking in front of people.
#ML #AI #MLsec #infosec #security #LLMshttps://www.youtube.com/watch?v=_Jsy7UBQv0c
https://berryvilleiml.com/2026/06/13/irony-the-us-government-issues-an-export-control-directive-for-fable-5-and-mythos-5/
You've seen all posts




