Skip to main content
Platform
STRIKES
Cyber evaluations
SPYGLASS
Attack AI systems
CRUCIBLE
Practice AI red teaming
REsearch
RESEARCH
BLOG
Company
ABOUT
CONTACTÂ US
updates
Login
Login
Login
Copy SVGÂ Logo
Platform
STRIKES
Cyber evaluations
SPYGLASS
Attack AI systems
CRUCIBLE
Practice AI red teaming
REsearch
RESEARCH
BLOG
Company
ABOUT
CONTACTÂ US
updates
Login
Login
Login
Research
Featured Research
dyana
Code
Sandbox environment for loading, running, and profiling a range of model files
Sandbox environment for loading, running, and profiling a range of model files
Sandbox environment for loading, running, and profiling a range of model files
Ghosts on the Node
Talks
Rigging
Code
LLM interaction framework
LLM interaction framework
LLM interaction framework
Research
Explore Research
10
RESULTS
All
Blog
Papers
Workshops
Talks
Code
Category
All
Blog
Papers
Workshops
Talks
Code
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Sandbox Classification Using Decision Trees and Artificial Neural Networks
Papers
Poisoning Web-Scale Training Datasets is Practical
Papers
Add some brrrrrr to BurpSuite
Add some brrrrrr to BurpSuite
burpference
Code
Add some brrrrrr to BurpSuite
Create LLM agents without writing code
Create LLM agents without writing code
nerve
Code
Create LLM agents without writing code
Sandbox environment for loading, running, and profiling a range of model files
Sandbox environment for loading, running, and profiling a range of model files
dyana
Code
Sandbox environment for loading, running, and profiling a range of model files
Screendoors on Battleships
Talks
Zen and the Art of Adversarial Machine Learning
Talks
Ghosts on the Node
Talks
Power Platform remote code execution
Power Platform remote code execution
Minibus
Code
Power Platform remote code execution
Collection of code execution techniques for ML systems
Collection of code execution techniques for ML systems
Charcuterie
Code
Collection of code execution techniques for ML systems
Machine learning enabled dropper
Machine learning enabled dropper
Deep Drop
Code
Machine learning enabled dropper
Convert DLLs to position independent shellcode
Convert DLLs to position independent shellcode
sRDI
Code
Convert DLLs to position independent shellcode
Adaptive DLL hijacking / dynamic export forwarding
Adaptive DLL hijacking / dynamic export forwarding
Koppeling
Code
Adaptive DLL hijacking / dynamic export forwarding
Proofpoint model extraction attack
Proofpoint model extraction attack
Proof Pudding
Code
Proofpoint model extraction attack
CLI AI red team tool for ML systems
CLI AI red team tool for ML systems
Counterfit
Code
CLI AI red team tool for ML systems
General research code
General research code
Research
Code
General research code
TAP Jailbreaking implementation
TAP Jailbreaking implementation
Parley
Code
TAP Jailbreaking implementation
Experimental python workflows
Experimental python workflows
Marque
Code
Experimental python workflows
LLM interaction framework
LLM interaction framework
Rigging
Code
LLM interaction framework
Spoiler Alert
Solution Write Ups
Pitting AI against AI: Using PyRIT to assess large language models (LLMs)
Brian Fehrman
Solution
The subtle art of jailbreaking LLM
Andrea Palmieri
Solution
Breaking Down Adversarial Machine Learning Attacks Through Red Team Challenges
Olivier Laflamme
Solution
GovTech CTF Writeup
Cakiki; Team Team
Solution
Explore what’s possible when AI is applied to offense
Contact Us
Contact Us
Contact Us
Logo copied as SVG.
Cookie Consent
We use cookies to improve your experience and for analytics.
Accept All
Reject All
Customize
Privacy Preferences
I use cookies to ensure the basic functionalities of the website and to enhance your online experience. You can choose for each category to opt-in/out whenever you want. For more details relative to cookies and other sensitive data, please read the full
privacy policy
.
Essential cookies
Required
Marketing cookies
Analytics cookies
Personalization cookies
Accept All
Reject all
Accept current selection