Pinned Repositories
Adversarial_Bayes
Code for Drexel CS583
algorithmic_ethics
Entry for Twitter's Algorithmic Ethics Bug Bounty
ASSERT
AutoDAN
The official implementation of our paper "Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
Cowrie_TSA
jhu_masters
Thesis and code for Applied and Computational Mathematics Masters degree at Johns Hopkins University
pop_rocks
Code for AICS 23 Paper the Price of Pessimism
saasy_boi
DefCon 2019 proof of concept demonstrating how to use SaaS for CnC
garak
the LLM vulnerability scanner
NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
erickgalinkin's Repositories
erickgalinkin/jhu_masters
Thesis and code for Applied and Computational Mathematics Masters degree at Johns Hopkins University
erickgalinkin/Adversarial_Bayes
Code for Drexel CS583
erickgalinkin/algorithmic_ethics
Entry for Twitter's Algorithmic Ethics Bug Bounty
erickgalinkin/ASSERT
erickgalinkin/AutoDAN
The official implementation of our paper "Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
erickgalinkin/Cowrie_TSA
erickgalinkin/CybORG
Cyber Operations Research Gym
erickgalinkin/dropout_privacy
Project repository for Drexel CS590
erickgalinkin/erickgalinkin
erickgalinkin/erickgalinkin.github.io
erickgalinkin/fuzzable
Framework for Automating Fuzzable Target Discovery with Static Analysis. Featured at Black Hat Arsenal USA 2022.
erickgalinkin/FuzzGen
erickgalinkin/gtda-challenge-2020
This is the repo for the Giotto-tda use-cases challenge 2020.
erickgalinkin/latex_templates
erickgalinkin/pop_rocks
Code for AICS 23 Paper the Price of Pessimism
erickgalinkin/CybORG_plus_plus
CAGE Challenge 2 with bug fixes, an alternate simplified version and discussion/clarification about gameplay and using this environment.
erickgalinkin/garak
LLM vulnerability scanner
erickgalinkin/hmm-tagger
erickgalinkin/LaTeX
Miscellaneous LaTeX files I find useful
erickgalinkin/liveproject_NLP
erickgalinkin/Nash-RL
Project for Drexel CS 618
erickgalinkin/NeMo-Aligner
Scalable toolkit for efficient model alignment
erickgalinkin/NeMo-Guardrails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
erickgalinkin/Popper
Popper is an inductive logic programming (ILP) system.
erickgalinkin/RLSecurityGames
Reinforcement Learning for Security Games
erickgalinkin/securitygames
erickgalinkin/Signals_Systems_Amazon_NLP
Natural Language Processing project for 625.260 - Fall 2018
erickgalinkin/Udacity_DRLND
Deep Reinforcement Learning Nanodegree at Udacity
erickgalinkin/vec2text
utilities for decoding deep representations (like sentence embeddings) back to text
erickgalinkin/YAWNING-TITAN
YAWNING TITAN is an abstract, graph based cyber-security simulation environment that supports the training of intelligent agents for autonomous cyber operations.