Red teaming
Red-teaming is the practice of testing a computer system from the perspective of an opponent to identify potential attack vectors.
Vulnerability Research Initiative (VRI)
UK government's cybersecurity program working with internal and external experts to test its tech
ETHIACK
Autonomous Ethical Hacking
AI Vulnerability Database (AVID)
An open-source, extensible knowledge base of AI failures
AI Risk and Vulnerability Alliance (AVAR)
As ARVA, our mission is to empower communities to recognize, diagnose, and manage vulnerabilities in AI that affects them.
Red teaming large language models (LLMs) for resilience to scientific disinformation
The red teaming event brought together 40 health and climate postgraduate students with the objective to scrutinise and bring attention to potential vulnerabilities in large language models (LLMs1 ).
Humane Intelligence
Humane Intelligence is a tech nonprofit building a community of practice around algorithmic evaluations.
Red Team Lab at Open Tech Fund
The lab focuses on improving the software security of projects that advance OTF’s Internet freedom goals by ensuring that code, data, and people behind the tools have what they need to create a safer...