tokarev-i-v Goto Github PK

gym-network_intrusion

This gym environment simulates network intrusion similar to that described in the NSL-KDD Dataset given in this link http://www.unb.ca/cic/datasets/nsl.html

gym-optimal-intrusion-response

A Simulated Optimal Intrusion Response Game

hamiltonian-nn

Code for our paper "Hamiltonian Neural Networks"

hands_game

There is my android game

haxss

A reinforcement learning based XSS injection prototype

ibm_quantum_challenge

IBM Quantum Challenge solutions

informationsecurityontology

Ontology of the area of ​​Information Security, formalized in the OWL language

jaws_modeling_3d1

Created with CodeSandbox

jotr

js_games

there are my games

jsqis

Javascript quantum information simulator

kaggles

Repo with my decisions for Kaggle Competitions.

keras-tuner

Hyperparameter tuning for humans

kill_rats

This is VK clicker.

klm_model

KLM protocol computer simulator

kursach_4

lamorel

Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).

langchain

⚡ Building applications with LLMs through composability ⚡

lapo

Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)

lightning

linevd

Statement-level deep learning model for automated software vulnerability detection in C/C++ (Accepted in MSR 2022)

linevul

A Transformer-based Line-Level Vulnerability Prediction

link

Link: Black-Box Detection of Cross-Site Scripting Vulnerabilities Using Reinforcement Learning

llama-recipes

Examples and recipes for Llama 2 model

llama-tot

Tree of Thought Experiment with LLaMa Models

llama_generative_agent

A generative agent implementation for LLaMA based models, derived from langchain's implementation.

llm.c

LLM training in simple, raw C/CUDA

llm4rl

A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM

lm-finetune

Код для файнтюна LM (rugpt, LLaMa, FRED T5) средствами transformers + deepspeed + LoRa

mab-malware

MAB-Malware an open-source reinforcement learning framework to generate AEs for PE malware. We model this problem as a classic multi-armed bandit (MAB) problem, by treating each action-content pair as an independent slot machine.