#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
sec5gloc/sec5glocAdversary-resilient deep learning architecture for secure 5G indoor localization, combining CNN and multi-head attention to defend against signal…
sej2020/manipulating-web-agentsResearch demonstration of indirect prompt injection attacks to control autonomous LLM-based web agents, with tools for trigger optimization and…
stair-lab/certified-unlearning-neural-networks-icml-2025Code for the paper Certified Unlearning for Neural Networks, ICML 2025
thinwayliu/multimodal-unlearnable-examplesThe code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)
suraj-ranganath/stealthrlStealthRL: RL framework for adversarially paraphrasing AI text to stress-test detector robustness.
yueliu1999/guardreasoner-vl[NeurIPS 2025] An official source code for paper "GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning".
ztcoalson/if-guide[NeurIPS '25] Code for Paper "IF-Guide: Influence Function-Guided Suppression of Harmful Training Data for Reducing LLM Toxicity"
adamsjack711-ux/pkgxrayPre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.
toxy4ny/delirium-ai-safety-benchmarkA diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…
ascit31/dark-moonAutonomous AI pentesting engine, continuous offensive security across web, cloud, AD & Kubernetes. Agentic reasoning + real exploit execution deliver…
l33tdawg/aetherAI Smart Contract Security Analysis and PoC Generation Framework
pikpikcu/aireconAIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual…
ryehr/rrc_steganographyProvably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…
jd0965199-oss/ethibenchEvaluation framework for AI penetration testing agents that measures validated vulnerability discovery using LLM-based semantic matching, bipartite…
0xblackash/cve-2026-42208CVE-2026-40487
pensarai/apexAI-powered offensive security testing using autonomous agents, directly in your terminal.
sunblaze-ucb/exploitgymExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
