Live data from Hacker News

AI browser extensions are a security nightmare

kolide.com

61–70 of 129 posts

Re: AI browser extensions are a security nightmare

#61
post #59
post #54

Actually, aren't all browser extensions a security nightmare? Or has something changed recently?

No, because a typical safe-to-run browser extension is written in such a way that it can be examined to see what it does. AI-based tools can’t be analyzed based on their code, so the only way to make them safe is by limiting their capabilities. Any such capability limit is likely to be either too constraining, not constraining enough, or require as much planning ability as the AI itself.

The problem is the permission system. Like apps, extensions have an all-or-nothing attitude to permissions. Browsers should allow the user to be more specific about permissions, and let extensions think the user gave more permissions than they actually did. E.g. if extension insists that they need "access to entire filesystem", the browser should make the extension believe they have access to the entire filesystem, but of course the entire thing is sandboxed and the user can restrict the access behind the scenes.

Without this feature, extensions will keep insisting they need access, and the user will eventually fall for it.

Re: AI browser extensions are a security nightmare

#65
post #61
post #59

Earlier quoted context omitted.

No, because a typical safe-to-run browser extension is written in such a way that it can be examined to see what it does. AI-based tools can’t be analyzed based on their code, so the only way to make them safe is by limiting their capabilities. Any such capability limit is likely to be either too constraining, not constraining enough, or require as much planning ability as the AI itself.

The problem is the permission system. Like apps, extensions have an all-or-nothing attitude to permissions. Browsers should allow the user to be more specific about permissions, and let extensions think the user gave more permissions than they actually did. E.g. if extension insists that they need "access to entire filesystem", the browser should make the extension believe they have access to the entire filesystem, b…

> Like apps, extensions have an all-or-nothing attitude to permissions

Browser extensions needs to declare their permissions. With Manifest V3 we’re seeing even more need to declare permissions.

Any extension cannot do anything not explicitly granted to it by the user upon installation.

Re: AI browser extensions are a security nightmare

#66

Earlier quoted context omitted.

> is it that some people define intelligence as >= human I just want to say that this seems to be how many, if not most people define intelligence internally. If an LLM gets something wrong or doesn't know something, then it must be completely unintelligent. (as if humans never get anything wrong!)

Like with humans, there are intelligent ways to be wrong and unintelligent ways to be wrong. LLMs do a whole lot of “wrong in a way that indicates it is not ‘thinking’ the way an intelligent human would.”

What's concerning about this is we are evaluating AI on a basis that humans are not subject to. LLMs in their current form are built on the knowledge of the internet, while humans have both the internet and realtime feedback from their own lives in the physical world. If a human brain could be trained the same way as an LLM, might it also connect seemingly unconnected ideas in a way that would appear as non-thought? Maybe, maybe not. LLMs seem to be biased heavily towards making best effort guesses on things it doesn't know about, whilst humans are far more modest in doing so. I just don't know if we're really at a point where we can conclusively decide that something isn't thinking just because it doesn't appear to be thinking by the standards we place upon ourselves.

Re: AI browser extensions are a security nightmare

#67

Earlier quoted context omitted.

Do you suppose it's possible that accessing the DOM to add a div implicitly requires access to page data?

I can see how many applications might want to read the page, but in my case it's not necessary. My extension tries to add a under the element, regardless of what's going on in the page. If there's no , my extension stops working but the browser keeps going. In short, if there were separate "read" and "write" permissions, I would only need "write". For privacy-concerned people, that's a very important distinction.

It would be more complex than that given you can write arbitrary JavaScript that can read anything it likes and send it anywhere.

Re: AI browser extensions are a security nightmare

#68
post #54

Actually, aren't all browser extensions a security nightmare? Or has something changed recently?

shout out to the Arc browser, which has it's own browser sandbox and WYSIWYG tools to build JS snippets that run in your browser. I'm not affiliated with them in any way, but they're really changing the way I look at browsing online.

Does that come on a CD along with Intel Arc GPUs? :D

Re: AI browser extensions are a security nightmare

#69
post #47

Earlier quoted context omitted.

In my field it's accepted (by some) that you write "AI" for your grant proposal and say "ML" when you talk to colleagues and want to be taken seriously. It feels a bit wrong to me, because as you say it's arguably a grift, in this case on the taxpayer who funds science grants. More charitably it might just be the applicant admitting that they have no idea what they are doing, and the funding agency seeing this as a g…

Most people outside of academia understand AI to include way more than just ML. People refer to the bots in video games as AI and they are probably a few hundred lines of straightforward code. I don't think there is anything wrong with using the colloquial definition of the term when communicating with funding agencies/the public.

I think you're entirely wrong about this. Using the term AI or artificial intelligence directly invokes several centuries of cultural baggage about golems, robots, Terminators, androids and cyborgs and Matrix-squid.

Saying "large language models" does not. Saying "giant correlation networks" does not. Not to be too Sapir-Whorfian, but the terminology we use influences our conversations: terrorists, guerillas, rebels, revolutionaries, freedom-fighters.

Post reply on HN