lm-fingerprint
wattocyber/lm-fingerprintUnique tool for fingerprinting Large Language Models based on their tokenizers and behavior.
ai-securityapi-securityinformation-gathering+3
wattocyber/lm-fingerprintUnique tool for fingerprinting Large Language Models based on their tokenizers and behavior.
bishopfox/deephackProof-of-concept tool for generating adversarial perturbations to exploit weaknesses in deep learning models, based on DEF CON 25 presentation.
nishitvp/better_opts_attacksAttack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…
sbamit/exponentiated-gradient-descent-llm-attackA novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.
l33tdawg/aetherAI Smart Contract Security Analysis and PoC Generation Framework
wang-yanting/agentwatcherCausal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…
vinsontang1/vultriageLLM-based vulnerability detection framework combining static code analysis (CFG, DFG, AST) with retrieval-augmented generation for automated…
sooryathejas/metatronAI-powered penetration testing assistant using local LLM on linux (Parrot OS)
anthropics/defending-code-reference-harnessSkills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
space0blaster/smartmapLLM based map for research, exploration and discovery.
ccss17/o3_finds_cve-2025-37899Artefacts for blog post on finding CVE-2025-37899 with o3
mrwadams/stride-gptAn AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE…