In a groundbreaking development, a team of Carnegie Mellon University researchers has demonstrated that large language models (LLMs) are capable of autonomously planning and executing complex network attacks, shedding light on emerging capabilities of foundation models and their implications for cybersecurity research.
The project, led by Ph.D. candidate Brian SingerOpens in new window, a Ph.D. candidate in electrical and computer engineering (ECE)Opens in new window, explores how LLMs—when equipped with structured abstractions and integrated into a hierarchical system of agents—can function not merely as passive tools, but as active, autonomous red team agents capable of coordinating and executing multi-step cyberattacks without detailed human instruction.
Read more…
Source: Carnegie Mellon University
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Hackers are spending millions on expired domains to enable malware scams
August 21, 2026
A domain name is the closest thing the web has to a credit history: age, inbound links, search visibility, and reputation all feed the reputation scores that security products consult before deciding whether a request is worth worrying about. New research from Infoblox Threat Intel claims this history has become a commodity with a market price, and that at least ...
- Medical records, SSNs, and bank details exposed in CareCloud data breach
August 21, 2026
Healthcare technology giant CareCloud has confirmed that a data breach earlier this year impacted more than 3.75 million people, making it one of the largest healthcare data incidents disclosed this year. The New Jersey-based company, which provides electronic health record (EHR) and practice management services, first flagged the intrusion in an SEC filing back in March, but the true scope ...
- Identity abuse through trusted communication channels
August 20, 2026
Identity has become a primary security boundary for most organizations, reducing the ability to solely trust other boundaries once associated with corporate networks. Users authenticate to cloud services using enterprise identities that provide access to collaboration platforms, business applications and sensitive data. With the adoption of software-as-a-service (SaaS) on the rise, people are shifting to ...
- CareCloud confirms 3.7M patients had their medical records stolen in data breach
August 19, 2026
Hackers have stolen the personal information and medical records of more than 3.75 million people in a data breach at health data giant CareCloud, the company has confirmed with federal regulators. The disclosure marks the first confirmation of the scale of the data breach, which is now confirmed to be the fifth-largest theft of health ...
- Defending against an active threat to Siemens S7 Series PLCs
August 19, 2026
This advisory relates to an active threat to Siemens S7 Series programmable logic controllers (PLCs). However, ongoing PLC targeting activity is broader than Siemens PLCs. All PLC owners and operators should apply relevant mitigations to reduce the risk to their devices and systems. The Siemens-specific content in this advisory should be understood and applied as ...
- ‘Proactive SIM’ cards can hijack smartphones, IoT devices and even EV chargers
August 18, 2026
A malicious SIM card can instruct the device it sits in to run commands of an attacker’s choosing, and on the cellular modules embedded in electric vehicle chargers, industrial routers, and car telematics units, essentially allowing it to take the entire device over. Researchers from the University of Birmingham and the German security firm Fuzzware demonstrated ...