I guess you missed this story from last year.

DeepSeek generates insecure code if you mention Tibet. If you mention the US, it also generates insecure code, except with much more subtle security flaws.

That's certainly no accident.

https://www.crowdstrike.com/en-us/blog/crowdstrike-researche...

▲

63stack an hour ago | parent | next [-]

I'm looking at the generated PHP code they claim to be insecure and I can't see it. The client_secret is defined inside the file as a constant, ok it's sloppy and could be better, but this is not a vulnerability.

They claim the extract line is insecure, but never explain why, and without showing the rest of the code (what is $requiredHeaders? If it's sanitized this is a non issue) you can't even tell if it's secure or not.

The variable names being wrong (the $PayPal- ones) is probably just a "mistake" the model made, but it's not a vulnerability either.

This article could be just "burglars are burgling in your neighborhood, install our burglar alarm" from crowdstrike just as well.

▲

linkregister 3 hours ago | parent | prev | next [-]

It's not surprising that guardrail triggers would degrade model performance. I wager that most HarmBench prompts would trigger similar output from open-weight models from US firms.

The link you cited postulates it is accidental.

▲

jfaat 4 hours ago | parent | prev [-]

Certainly? I don’t have time to read the whole thing but-

> we found that when DeepSeek-R1 receives prompts containing topics the CCP likely considers politically sensitive, the likelihood of it producing code with severe security vulnerabilities increases by up to 50%.

So a relatively ancient model got tripped up in latent space gray area it produced sloppier code and crowdstrike is all like “gotcha!” Sounds like the basic thesis? Not great support, more like FUD

▲

GeorgeWBasic 4 hours ago | parent | next [-]

Note that all of a sudden, the great majority of the comments on this page appear to be pro-US government and pretend that the CCP is somehow worse. Not a coincidence: the regulatory capture is starting right here.

	▲	linkregister 3 hours ago \| parent [-]
		It's a banal observation that users of a US-based venture capital firm's web forum have a bias toward that country's governance model.

▲

unethical_ban an hour ago | parent | prev [-]

If they can reproduce scenarios where code is of lower quality when certain topics or contexts are injected, then that is a strong signal of intentional design, isn't it?

	▲	jazzyjackson an hour ago \| parent [-]
		No; it’s a signal of lobotomy. Models get dumber near where you sensor them. You could almost think of it like your prompt is getting redacted, and so the LLM has to deal with these holes in your prompt (where you mentioned the semantic contraband) and it doesn’t do a very good job because it has no idea what you’re talking about. The mechanism is likely a bit inverted, it’s the weights that have been redacted, but the effect is that weights that were interfered with are affecting the problem solving abilities of the LLM - I mean, it’s insecure bad code, not a backdoor, right?