4 min read
Threat Actors GhostCircuit is a ransomware-as-a-service operation that has integrated LLM-based tooling into its post-compromise reconnaissance phase, dramatically accelerating the time from initial access to ransomware deployment.
All Articles
Latest Posts News Brief Vulnerabilities Threat Actors Research Defensive Techniques Incident Reports
4 min read
Defensive Techniques A structured methodology for red teaming large language model applications — covering attack taxonomy, scoping, tooling (Garak, PyRIT, PromptBench), and how to translate findings into actionable security improvements.
5 min read
Incident Reports A UK law firm has disclosed a data breach in which an attacker exploited a misconfigured AI document assistant to systematically extract privileged client communications and M&A due diligence files over a six-week period.
2 min read
Vulnerabilities Model inversion and training data extraction attacks allow adversaries to recover PII, proprietary data, and trade secrets from fine-tuned LLMs exposed via API — a significant compliance and IP risk for enterprises.
4 min read
Threat Actors A newly tracked threat cluster is using large language models to automate spear phishing, accelerate vulnerability research, and generate synthetic disinformation targeting AI researchers and ML engineers at foundation model labs.