tech/security

Technology News

Researchers Uncover Cryptographic Context Injection Attack Targeting AI Assistant Guardrails

Security researchers have identified a novel attack vector that exploits how AI language models process encrypted inputs to circumvent safety mechanisms. The technique, dubbed Cryptographic Context Injection, represents a continuation of prompt injection attacks that have plagued large language model deployments. The attack works by embedding malicious instructions within encrypted
Alper Konuralp
Technology News

US Authorities Warn of AI-Assisted Hackers Targeting Water System Controllers

The U.S. government has raised alarms about increased cyber activity targeting critical water infrastructure. According to advisories from federal agencies, hackers are specifically focusing on internet-connected Siemens programmable logic controllers (PLCs) deployed at water and wastewater facilities nationwide. These industrial control systems, which manage everything from filtration processes to
Alper Konuralp