TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Bypassing Gmail's spam filters with ChatGPT

207 pointsby neelcover 2 years ago

22 comments

4gover 2 years ago
Using these tools to mitigate spam is as likely a scenario as this, imagine that every spam mail receives a masterfully crafted response showing utter fascination and interest in SEO, or helping out a Nigerian prince. Every phone call to an unregistered number is answered by an artificial, frail, and forgetful lady that is trying her best to register gift cards.<p>When reporting an e-mail as spam it will not only block the address but waste the spammers time, rendering the actions unprofitable.
评论 #34481950 未加载
评论 #34482014 未加载
评论 #34482822 未加载
评论 #34486145 未加载
评论 #34482064 未加载
评论 #34482147 未加载
评论 #34481942 未加载
评论 #34483734 未加载
评论 #34486454 未加载
评论 #34481960 未加载
评论 #34486464 未加载
评论 #34483413 未加载
评论 #34482519 未加载
评论 #34481909 未加载
评论 #34481978 未加载
评论 #34482238 未加载
mfiover 2 years ago
&gt; I’m no AI or machine learning expert so I don’t know how it works. But I am also worried that spammers could use ChatGPT to get around Gmail and Outlook’s spam filters.<p>This will not only increase the spam-problem, but will most likely be used to scale and do targeted phishing attack as well. I wrote an extensive article[0] where I analyzed this. And to no surprise, GPT-3 can be used to generate dynamic phishing campaigns on the fly in multiple languages, classify email responses, improve email thread hijacking attacks etc.<p>[0] <a href="https:&#x2F;&#x2F;www.xorlab.com&#x2F;en&#x2F;blog&#x2F;why-ai-powered-phishing-will-become-a-serious-security-issue-for-your-organization" rel="nofollow">https:&#x2F;&#x2F;www.xorlab.com&#x2F;en&#x2F;blog&#x2F;why-ai-powered-phishing-will-...</a>
评论 #34481149 未加载
评论 #34482941 未加载
评论 #34481140 未加载
jeffbeeover 2 years ago
People are overestimating the importance of the message body in spam classification. The stuff that appears in your spam label on gmail is what google considered marginal, almost ham. The vast, vast majority of what they think is spam is rejected with temporary failure codes at SMTP time and never gets delivered with any label. IP reputation and other related metadata features are the key features in spam classification, and repeatedly sending different messages is not a valid test of whether the body looks spammy or not.
评论 #34481369 未加载
评论 #34482017 未加载
评论 #34484902 未加载
评论 #34480524 未加载
narratorover 2 years ago
As I have said before, the future will have two kinds of AI everywhere.<p><i>Their AI</i> to get you to buy something, do something, believe something, or in a warzone to kill you and <i>Your AI</i> to protect you from <i>Their AI</i>. Reality may even become so dangerous and illusory that humans lose a lot of their agency to <i>Your AI</i>.
thyroxover 2 years ago
All this can be done since GPT3 API has been available.<p>I see a lot of people thinking chatgpt is something new capable of such stuff but GPT3 is far less restrictive and has been able to do all this for almost an year now.
评论 #34481234 未加载
cosmojgover 2 years ago
Is it finally time for Hashcash[1]&#x2F;PennyPost[2]?<p>[1] <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Hashcash" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Hashcash</a><p>[2] <a href="https:&#x2F;&#x2F;pennypost.sourceforge.net&#x2F;PennyPost" rel="nofollow">https:&#x2F;&#x2F;pennypost.sourceforge.net&#x2F;PennyPost</a>
Tagbertover 2 years ago
AFAIK all it takes to bypass Gmails spam filters is to resend the same scammy email that was Flagged but using a different email address. I get the same kind of scammy emails, flag them as spam, and then a couple days later, Gmail lets the same email in though it is coming from a different 123134r12345124@blahblah.com address.
评论 #34483466 未加载
评论 #34482608 未加载
marginalia_nuover 2 years ago
Anecdotally, almost every email I see in my gmail inbox is advertisement of some sort. There&#x27;s newsletters I never signed up for, special offers from companies I&#x27;ve never had dealings with, it never ends.<p>Some of it hasn&#x27;t even been sent to me as an email, but shows up in the inbox as though it was an email.<p>Granted, there&#x27;s fewer scam emails than in my non-gmail inbox, but man is there a lot of spam.
sirsinsalotover 2 years ago
If we thought the signal vs noise problem was bad, wait until 90% of data is banal AI drivel drowning out any semblance of authenticity.<p>Boring, brown, homogeneous noise
评论 #34483677 未加载
Crystalinover 2 years ago
well, you don&#x27;t need ChatGPT for that. I receive daily scam in my gmail with 99% the same content each time (and i mark it spam each time)... the worst part ? the server serving it is google (but the email attached to it is always a different obscure email)
mk_stjamesover 2 years ago
I must be in the extreme minority upon reading comments on email spam, as I almost never receive a spam message in my main gmail inbox that is truly spam and not something I&#x27;m getting an email for because I lazily opted-in to a mailing list or was put on one due to association with a product. Actual, oldschool spam (Nigerian princes, claim your prize etc) literally never gets to my inbox. Maybe I&#x27;m just not a popular person. Or maybe I&#x27;ve kept my email private enough that it doesn&#x27;t get scraped for such things? I don&#x27;t understand the discrepancy between my experience and so many others here.
_glassover 2 years ago
On the other hand it&#x27;s easy to detect ChatGPT, at least for now <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;openai-detector" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;openai-detector</a>
评论 #34486674 未加载
londons_exploreover 2 years ago
I don&#x27;t think message content is weighted very heavily in modern spam filters...<p>Things like IP reputation, sender reputation, and various SPF-like headers are far more important.
评论 #34484684 未加载
steveBK123over 2 years ago
Interpretations I&#x27;ve seen of ChatGPT type tools, and playing around with it, I would sum up as &quot;reducing the marginal cost of creating BS to $0&quot;. Great for content farms, spam, disinfo&#x2F;propaganda campaigns.<p>Stuff where it doesn&#x27;t have to be correct, have a high hit rate, or even be edited. Just need to produce plausible enough sounding, human-like content.
wolverine876over 2 years ago
Think what can be done with an AI trained on all the data that&#x27;s been collected about you.
评论 #34481971 未加载
评论 #34484908 未加载
graypeggover 2 years ago
I think the future model of email will be spam-by-default, where you whitelist senders as you need them.<p>Already doing that with hey email [0] where you screen all incoming senders.<p>[0] <a href="https:&#x2F;&#x2F;hey.com" rel="nofollow">https:&#x2F;&#x2F;hey.com</a>
low_tech_loveover 2 years ago
Considering how much crap I get in my Gmail inbox, doesn’t seem like it’s a hard task. Seriously, my Gmail account is borderline useless nowadays.
okasakiover 2 years ago
If you want to spam gmail you can just share documents with people or add events to their calendar. Apparently there&#x27;s no way to stop this.
natchover 2 years ago
I don’t think ChatGPT is really needed here.<p>Gmail’s spam filters are Google’s weakest tech. At least I don’t know of anything worse.
评论 #34482479 未加载
sorry_outta_gasover 2 years ago
This is about all its&#x27; good for, it won&#x27;t even write sexy fan fiction for me
评论 #34484914 未加载
butzover 2 years ago
Whoever is doing this, please stop. Thank you.
jokoonover 2 years ago
only way to make email work is to let the user choose what domain they trust, and maybe to have a feature where the user must whitelist addresses.
评论 #34481202 未加载
评论 #34482816 未加载
评论 #34481168 未加载