Tools

giskard-ai/giskard-oss

🐢 Open-Source Evaluation & Testing library for LLM Agents

siyuanli00/intact

Research code reproducing multi-turn LLM jailbreak experiments (FITD, MRCJ, ActorAttack, X-Teaming) from the SoK intent-oriented systematization…

protectai/rebuff

Multi-layered prompt injection detector for AI applications using heuristics, LLM-based analysis, vectorDB attack signatures, and canary token leak…

ryehr/hitms_steganography

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

trailofbits/anamorpher

image scaling attacks for multi-modal prompt injection

chaos-boops/clpstnet

CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learning

lightless-labs/third-thoughts

Research toolkit for analyzing AI agent behavioral patterns through multi-disciplinary corpus analysis. Parses session logs, runs 23 analytical…

unknownhl/deepguard

Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

cognitive-functors/c4-meta-system

Production AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…

mcastens/alycon-threat-landscape

Training-free anomaly detection framework using Shannon Entropy, Fisher Information, and Wasserstein Distance to map system states into geometrically…

vinsontang1/vultriage

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

hydradragonantivirus/hydradragonav-mobile

Android Antivirus which doesn't require root, adb, ca install and cloud with many features and ways to detect more zero-day malware

qkrrkd90-source/weavemark

Reference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…

safelineman/agentic-soc-simulation

AI 驱动的 SOC 仿真平台