Current AI security news, vulnerabilities and research
The disruption of the Tycoon2FA phishing platform in mid-2026 has significantly altered attack vectors, forcing threat actors to pivot toward Teams-based social engineering while employing more automated multi-stage chains.
A recent collaboration between OpenAI and Hugging Face highlights the critical need for robust defensive measures when evaluating large language models, revealing advanced cyber capabilities that can compromise AI systems.
The Microsoft Security Blog introduces Project Perception, marking a paradigm shift from traditional perimeter-based security to dynamic trust frameworks designed specifically for complex agentic systems and Large Language Models (LLMs). The article emphasizes the necessity of redefining Trust Boundaries within intricate Tool Call chains.
13 results
The Microsoft Security Blog introduces Project Perception, marking a paradigm shift from traditional perimeter-based security to dynamic trust frameworks designed specifically for complex agentic systems and Large Language Models (LLMs). The article emphasizes the necessity of redefining Trust Boundaries within intricate Tool Call chains.
This paper identifies a new attack vector scenario called 'Denial of Deadline', where targeted workload bursts push the latency limit for the slow, high-accuracy inference path beyond its deadline. This causes high-quality predictions to be discarded and drastically reduces overall system utility.
This edition summarizes key developments in AI security. The focus is on a shift in phishing tactics toward Teams-based social engineering and a new partnership between OpenAI and Hugging Face to improve safety standards during model evaluation.
The disruption of the Tycoon2FA phishing platform in mid-2026 has significantly altered attack vectors, forcing threat actors to pivot toward Teams-based social engineering while employing more automated multi-stage chains.
The upcoming event, Black Hat 2026, brings together over 22,000 security practitioners specializing in offensive and defensive strategies for enterprise infrastructure.
Microsoft has partnered with AXA XL to integrate Incident Response services directly into the insurance policyholder ecosystem, enabling organizations to coordinate technical remediation alongside business continuity decisions.
A recent collaboration between OpenAI and Hugging Face highlights the critical need for robust defensive measures when evaluating large language models, revealing advanced cyber capabilities that can compromise AI systems.
This edition focuses on the evolution of red teaming methodologies and new definitions for threats in AI-enabled systems.
Microsoft participated in Black Hat USA 2026 to address critical threats involving adversarial machine learning, data poisoning, and compromised cryptographic wallets within global software supply chains.
Security agent evaluations are often incomplete because they only measure peak offensive capability under generous inference budgets. In operational security, every reasoning step, tool call, or telemetry query consumes budget that limits actual success rates.
A vulnerability in Drupal AI (versions before 1.0.5) allows OS Command Injection due to improper neutralization of special elements.
This paper argues that traditional penetration testing is insufficient for AI systems, as adversaries can alter system behavior through prompt injection or data poisoning without compromising the underlying infrastructure. It proposes a new framework focused on violations of operational behavioral objectives.