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. "The TokenBreak attack targets a text classification model's tokenization...

Telegram will hand over user details to law enforcement

Last month we reported how Telegram CEO Pavel Durov was indicted on charges of complicity in the distribution of child sex abuse images, aiding organized crime, drug trafficking, fraud, and refusing lawful orders to give information to law enforcement. Now, in a potentially related development,...