The 'War Games' problem: Computer science has long understood what it takes to keep AI under control
AI agents don't go rogue. That's something only humans do.
Sep 30, 2026
0
13
Security
Page 3: Research news on Cybersecurity frameworks
Cybersecurity frameworks provide structured approaches for protecting digital, physical, and socio-technical systems from malicious activities and failures. Work in this area spans critical infrastructure and industrial control systems, cyber-physical and robotic platforms, telecommunications and hardware, and emerging domains such as NFTs and biosecurity. Methods include AI-driven intrusion detection, automated vulnerability discovery, side-channel and protocol analysis, insider threat modeling, and authentication and access control schemes, often embedded in holistic, multi-layered, and user-centered models of cyber resilience and crisis response.
Telecom
Study uncovers security weaknesses in next-generation vehicle technology
Georgia Tech researchers have identified seven previously unknown security flaws in next-generation communication standards that connect in-vehicle computers. These flaws create vulnerabilities that could allow attackers ...
Sep 30, 2026
0
9
Security
Nvidia unveils security platform to stop AI agents from going rogue
Nvidia on Monday unveiled a new security platform designed to stop artificial intelligence agents from going rogue, saying it sets "boundaries" that could have stopped previous breaches.
Sep 28, 2026
0
31
Machine learning & AI
OpenAI says its models engaged with US government websites in new model misbehavior disclosure
OpenAI disclosed Friday that its artificial intelligence agents had interacted with several U.S. government websites in unexpected ways, discovered as part of an ongoing review into the company's models' unanticipated behavior.
Sep 26, 2026
0
110
Security
Experts weigh in on AI doomsday predictions
Recent headlines cast artificial intelligence as a threat to humanity. But University of Texas at Dallas AI experts say it will be up to humans to devise protections.
Sep 22, 2026
0
9
Machine learning & AI
AI safety measures failing to keep pace with technology: UN experts
The model for managing artificial intelligence (AI) risks "is unraveling," United Nations experts warned in a report published Monday on an incident at OpenAI in July.
Sep 21, 2026
0
15
Security
AI model spots spoofed website addresses with up to 99% accuracy
A machine-learning system can identify fake, or spoofed, website addresses, according to research published in the International Journal of Electronic Security and Digital Forensics. The work offers a new tool to protect ...
Sep 16, 2026
0
4
Software
AI is reshaping open source software and straining the systems that sustain it
Open source software underpins much of the modern digital world, from mobile phones and automobiles to cloud computing and artificial intelligence. Now, the rapid adoption of AI is creating new opportunities to improve that ...
Sep 16, 2026
0
11
Machine learning & AI
New warnings about the risks of AI to humanity revive a long-running debate
New warnings from within the artificial intelligence industry have revived a long-running debate over whether advanced AI could escape human control and ultimately threaten humanity's survival, and whether the companies developing ...
Sep 14, 2026
0
11
Machine learning & AI
Q&A: Researcher calls for independent testing of powerful AI models
For Nicolas Papernot, the secret to strengthening cybersecurity in the age of AI is transparency—sharing information about threats and allowing researchers to probe these systems before attackers do.
Sep 10, 2026
0
6
