Fléchette Labs

R&D and consulting for cybersecurity, and AI safety and security. #BT6

About Fléchette

Fléchette Labs is led by Flétcher, who is part of the top AI red team BT6, and has built and led top-performing red teams in government and Fortune 50 organizations. With extensive experience in offensive security operations, Flétcher brings a unique perspective to the evolving challenges of AI safety and security.

Our team specializes in the intersection of artificial intelligence and security, combining deep technical expertise with practical experience from high-stakes environments. We understand both the offensive and defensive aspects of modern security challenges, particularly as they relate to AI systems.

Fléchette Labs is an R&D lab focused on AI safety and security research and assessments. We serve customers through consulting engagements and research projects, providing actionable insights and solutions to complex security challenges.

Our approach is grounded in real-world experience and cutting-edge research. We work with organizations to not only identify vulnerabilities but also to develop robust strategies for protecting AI systems and leveraging AI for enhanced security postures.

Our Services

Technical Consulting

Primarily serving customers in Government, Defense, and highly-regulated industries:

  • Cybersecurity and offensive security, including how to use AI to attack or defend systems
  • General consulting on AI security and safety
  • Strategic guidance on AI adoption - policies, tech stacks, and organizational goals
  • Agent development and training for specialized tasks

Research

AI research projects with a principal focus on:

  • AI interpretability and explainability
  • Security vulnerabilities in AI systems
  • Novel attack and defense methodologies

Contact Us

Or send an email directly to the team at c2l0ZWlucXVpcmllc0BmbGVjaGV0dGVsYWJzLmNvbQo=