Iranian-Linked Hackers Target Minnesota Water Infrastructure in Major Escalation of Cyber Hostilities

The stability of American critical infrastructure has faced a renewed and sophisticated challenge as a wave of cyberattacks paralyzed over 30 municipal water and wastewater systems across Minnesota. Emerging intelligence reports, including a classified-for-official-use memo circulated to the Water Information Sharing and Analysis Center (WaterISAC), have formally linked these intrusions to Iranian state-sponsored actors. This […]

8 mins read

Iranian State-Linked Hackers Target Minnesota Water Utilities in Escalation of Critical Infrastructure Cyberattacks

The digital landscape of American critical infrastructure faces a perilous new reality as federal and state intelligence agencies investigate a coordinated series of cyberattacks against municipal water and wastewater facilities across Minnesota. A confidential memo circulated within the Water Information Sharing and Analysis Center (WaterISAC) has officially linked these breaches to Iran, marking a significant […]

8 mins read

Defenders are turning the tables on AI hackers by adopting malicious prompt injection tactics as a powerful new defensive strategy

For years, prompt injection has been the primary weapon in an attacker’s arsenal, a digital Trojan horse designed to subvert large language models (LLMs) by forcing them to bypass safety protocols. By embedding malicious instructions into seemingly innocuous emails, calendar invites, or web documents, hackers have successfully tricked AI agents into exfiltrating sensitive data, executing […]

8 mins read

Defenders turn the tables on AI hackers by using prompt injections to disable malicious agents

For years, prompt injection—the practice of embedding malicious commands into data to manipulate large language models (LLMs)—has been the primary weapon for cybercriminals looking to hijack autonomous AI agents. By slipping a well-crafted instruction into a seemingly benign calendar invite or email, attackers could coerce an LLM into exfiltrating sensitive corporate data or executing unauthorized […]

8 mins read