red team
GPT-5.6-Cyber refuses security researchers’ requests far less often
GPT-5.6-Cyber is a new OpenAI model built on GPT-5.6 Sol, trained to find zero-day vulnerabilities and build exploit chains, with fewer refusals on higher-risk, dual-use work. …
Your security vendor gets the frontier cyber model, you get the findings
Selected red team specialists can now use OpenAI’s cyber models to find and exploit weaknesses in client applications and infrastructure. Those clients never get the …
GPT-Red beat human red teamers on a prompt injection test
GPT-Red is an automated red-teaming model that OpenAI trains to find prompt injection weaknesses. It works the way a human red-teamer does. It sends a prompt, watches how a …
Microsoft open-sources tools for designing and testing AI agents
Microsoft has open-sourced two tools aimed at bringing security discipline to AI agent development: Clarity, a structured design review tool, and RAMPART, a continuous testing …
AIMap: Open-source tool finds and tests exposed AI endpoints
Public-facing Ollama servers, MCP endpoints, and inference proxies have multiplied across the internet over the past year, often deployed without authentication or rate …
Automated LLM red teaming gets a learning layer
Automated red teaming of large language models has settled into a familiar pattern over the past two years. An attacker model generates jailbreak attempts against a target …
Scenario: Open-source framework for automated AI app red-teaming
Enterprises running customer service bots, data analytics agents, and other AI-driven applications in production handle sensitive records and connect to core business systems …
Training an AI agent to attack LLM applications like a real adversary
Most enterprise software development teams now ship AI-powered applications faster than traditional penetration testing can keep up with. A security team with 500 applications …
Kali Linux 2026.1 ships BackTrack mode, eight new tools, and a kernel upgrade to 6.18
Penetration testers running Kali Linux have a new release to work with. Version 2026.1 delivers the annual theme refresh, a new BackTrack-inspired mode in kali-undercover, …
BlacksmithAI: Open-source AI-powered penetration testing framework
BlacksmithAI is an open-source penetration testing framework that uses multiple AI agents to execute different stages of a security assessment lifecycle. A multi-agent …
Picking an AI red teaming vendor is getting harder
Vendor noise is already a problem in traditional security testing. AI red teaming has added another layer of confusion, with providers offering everything from consulting …
NVIDIA research shows how agentic AI fails under attack
Enterprises are rushing to deploy agentic systems that plan, use tools, and make decisions with less human guidance than earlier AI models. This new class of systems also …
Featured news
Resources
Don't miss
- A hollowed out data layer is making CISOs fly blind into AI attacks
- Hazmat: Open-source containment for AI agents
- Cisco fixes vulnerability exploited to DoS its firewalls (CVE-2026-20349)
- Four corporate investigation mistakes organizations make under pressure
- A stranger has been reading Salesforce and ServiceNow portals worldwide for 17 months