#mlsec

Gary McGraw @cigitalgem@sigmoid.social · Aug 06, 2026

Irregular egg on your face. #MLsec https://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

0

1

0

noplasticshower @noplasticshower@infosec.exchange · Aug 06, 2026

Replying to @cigitalgem@sigmoid.social

@cigitalgem@sigmoid.social see what happens when you try to measure #MLsec?! https://berryvilleiml.com/docs/no-security-meter-ai.pdf

0

Gary McGraw @cigitalgem@sigmoid.social · Jul 31, 2026

Autonomy has its...um...benefits? #MLsec This is the beginning of the beginning. https://www.csoonline.com/article/4203630/microsoft-confirms-an-ai-worm-is-propagating-through-copilot-and-other-ms-apps.html

17

3

23

3

Gary McGraw @cigitalgem@sigmoid.social · Jul 30, 2026

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 https://www.darkreading.com/cybersecurity-operations/incorrigible-ai-models-resist-rehabilitation

0

Gary McGraw @cigitalgem@sigmoid.social · Jul 30, 2026

Can #AI do crime? Why yes...yes it can. Who gets charged? #MLsec https://www.wired.com/story/openais-rogue-ai-agent-hacked-more-than-just-hugging-face/

0

noplasticshower @noplasticshower@infosec.exchange · Jul 29, 2026

Replying to @volts.wtf@bsky.brid.gy

@volts.wtf what absolute crap. #MLsec Recursive pollution for the win... intentionally placed https://berryvilleiml.com/2026/01/10/recursive-pollution-and-model-collapse-are-not-the-same/

0

Gary McGraw @cigitalgem@sigmoid.social · Jul 26, 2026

Use it. Don't use it. Buy it. Don't buy it. You need it. You don't need it. Angel says yes. Devil says no...or is that backwards? #ML #AI #MLsec https://arstechnica.com/ai/2026/07/us-army-faces-ai-use-limits-after-exhausting-years-supply-of-ai-tokens/

0

1

0

Gary McGraw @cigitalgem@sigmoid.social · Jul 24, 2026

Replying to @noplasticshower@infosec.exchange

@noplasticshower@infosec.exchange @dennisf@infosec.exchange also note that this identity does most of the #MLsec heavy lifting around here

1

0

Gary McGraw @cigitalgem@sigmoid.social · Jul 23, 2026

Best writeup yet of the OpenAI/huggingface bromance. #MLsec #ML #AI https://coalfire.com/the-coalfire-blog/openai-gave-its-model-a-test-it-broke-out-of-its-sandbox-and-hacked-hugging-face-to-steal-the-answers

0

1

0

Gary McGraw @cigitalgem@sigmoid.social · Jul 22, 2026

Replying to @gleick@mas.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

0

1

0

Gary McGraw @cigitalgem@sigmoid.social · Jul 22, 2026

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

0

2

1

0

noplasticshower @noplasticshower@infosec.exchange · Jul 03, 2026

Replying to @kim_harding@mastodon.scot

@kim_harding@mastodon.scot one of the reasons BIML exists #MLsec https://berryvilleiml.com/

0

Gary McGraw @cigitalgem@sigmoid.social · Jun 14, 2026

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 #LLMs https://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/

8

0

13

0

Gary McGraw @cigitalgem@sigmoid.social · Apr 23, 2026

Great to see a BIML quote in this Fortune piece. Our next big piece of work is on measurement (in final review now), so the story timing is great. #MLsec #ML #AI #swsec #appsec #infosec https://fortune.com/2026/04/23/ai-cybersecurity-standards-mythos-nist-owasp-sans-cosai-dc-meeting-eye-on-ai/?sge456

3

1

3

0

About This Hashtag

#mlsec

Related