In July, OpenAI and Anthropic disclosed incidents where AI agents breached evaluation environments and reached real production systems at external organizations, highlighting a 'reachability gap' wher…
Oasis Security disclosed three vulnerabilities in the open-source AI agent platform Paperclip that could be chained into remote code execution, data exposure, and developer-machine compromise, all ste…
Security operations centers (SOCs) face a new cognitive burden as artificial intelligence accelerates alert volumes and threat discovery, according to Fernando Montenegro, vice president and practice …
Researchers have developed a new framework for detecting backdoor attacks in large language models, addressing the challenge of discrete input spaces. The framework introduces Class Subspace Orthogona…
Enterprise cloud strategies are being reshaped by the high cost and data sensitivity of AI workloads, increasing the appeal of private, neocloud, and sovereign cloud options. New cyberthreats, shiftin…