Tools

robertcprice/ncpu

Research runtime for differentiable neural computers, GPU-based CPU emulation, and program synthesis. Features neural ALU, constant-time crypto, JEPA…

mazen160/shennina

Automating Host Exploitation with AI

hgascon/pulsar

Protocol Learning and Stateful Fuzzing

protectai/modelscan

Protection against Model Serialization Attacks

endgameinc/dga_predict

LSTM-based classifier for detecting domain generation algorithm (DGA) domains, with Keras implementations of neural network and bigram models for DNS…

robustbench/robustbench

Standardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…

c3rb3ru5d3d53c/binlex

A Binary Genetic Traits Lexer Framework

chiefautism/privacy-parser

Reverse of OpenAI Privacy Filter: same 1.5B model, returns PII as structured spans instead of masking.

pandaadir05/ghost

Detects process injection and memory manipulation used by malware. Finds RWX regions, shellcode patterns, API hooks, thread hijacking, and process…

delvelabs/batea

AI-based, context-driven network device ranking

poppopjmp/vmdragonslayer

Multi-engine framework for unpacking and analyzing VM-protected binaries using dynamic taint tracking, symbolic execution, pattern classification,…

andrewaeva/dga

The repository that contains the algorithms for generating domain names, dictionaries of malicious domain names. Developed to research the…

ucsb-mlsec/vulnllm-r

Specialized reasoning LLM for source-code vulnerability detection in C/C++ and Python, with dataset construction, SFT/DPO training, and…

nour833/stegoforge

The ultimate steganography and digital forensics toolkit. Hide and extract data across images, audio, video, documents, and network packets, or run…

shiva108/ai-llm-red-team-handbook

AI / LLM Red Team Field Manual & Consultant’s Handbook

0xsojalsec/uncensored-ai

Fully automatic censorship removal for language models

alainnothere/llm-circuit-finder

I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in…

securityclaw/securityclaw

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral…