22
New TokenBreak Attack Bypasses AI Moderation with Single-Character Text Changes
(thehackernews.com)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 12 Jun 2025
22 points (95.8% liked)
Cybersecurity
7528 readers
13 users here now
c/cybersecurity is a community centered on the cybersecurity and information security profession. You can come here to discuss news, post something interesting, or just chat with others.
THE RULES
Instance Rules
- Be respectful. Everyone should feel welcome here.
- No bigotry - including racism, sexism, ableism, homophobia, transphobia, or xenophobia.
- No Ads / Spamming.
- No pornography.
Community Rules
- Idk, keep it semi-professional?
- Nothing illegal. We're all ethical here.
- Rules will be added/redefined as necessary.
If you ask someone to hack your "friends" socials you're just going to get banned so don't do that.
Learn about hacking
Other security-related communities !databreaches@lemmy.zip !netsec@lemmy.world !securitynews@infosec.pub !cybersecurity@infosec.pub !pulse_of_truth@infosec.pub
Notable mention to !cybersecuritymemes@lemmy.world
founded 2 years ago
MODERATORS
The case I know of a company wanting to get the "efficiency" of using chatbots instead of people but not the responsibility of one, is Air Canada. They were held responsible in that case of their AI agent's policy hallucinations. Though the customer had to go through many hoops to get to that point and probably others were affected without due recourse.
What a brass neck on them - shocking they couldn't see it and decide to settle quietly instead.
Best thing I've read all day, cheers :)