Security news aggregator

Latest cybersecurity reporting from selected sources.

Yasna brings together recent headlines from selected sources and makes them easier to sort with tags, filters, and search.

1 headlines in this view

Showing 1 most recent headlines Filtered view

The Hacker News 1 year, 1 month ago

New TokenBreak Attack Bypasses AI Moderation with Single-Character Text Changes

Cybersecurity researchers have discovered a novel attack technique called TokenBreak that can be used to bypass a large language model's (LLM) safety and content moderation guardrails with just a single character change

More from The Hacker News 13 Jun 2025, 1:52 a.m. Artificial Intelligence Bypass Research Strategy Vulnerability

Latest cybersecurity reporting from selected sources.

Refine the feed

Volume over time

Fresh headlines available

New TokenBreak Attack Bypasses AI Moderation with Single-Character Text Changes