AI Security

owasp/owasp-subtractive-hardening-top-10

The OWASP Subtractive Security Top 10 Project is an initiative to identify, document, and promote the highest-impact opportunities for reducing cyber…

yashmahajan10/llm-differential-privacy-gateway

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

usmannasir/cyberpanel

Cyber Panel - The hosting control panel for OpenLiteSpeed

owasp/owasp-model-card-security-standard

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

bytespulse-oe/wp2shell-hestia-scanner

Read-only WordPress security scanner for HestiaCP servers. Detects wp2shell compromise indicators (CVE-2026-63030 / CVE-2026-60137) across all hosted…

spiralbl0ck/ai_hacking

Collection of CVE(work) on tenserflow binary pwning it

vikasudasi/exfil-scan

Scan LLM outputs and AI-generated content for data exfiltration signals (EchoLeak, CVE-2025-32711) before they reach users or downstream systems

afterquery/vader

Human-evaluated benchmark for assessing LLM performance on real-world vulnerability identification, explanation, and remediation across 15+ languages…

alphawarheads/watermark_spoofing

Research code and dataset (WSD) for evaluating audio watermarking impact on anti-spoofing, using wav2vec2 XLS-R and knowledge-preserving learning.

andyshaw01/poisoncraft

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

carol-long/cc_watermark

Implementation of optimal coupling-based distortion-free text watermarking to embed detectable signals in LLM-generated text while preserving quality.

erroristotle/dvdr_llm

Ensemble framework for software vulnerability detection and repair using multiple large language models, with consensus analysis and evaluation tools…

hondamunigeprasannasilva/attack-attention

[CVPR 2025-ADVML] Official Repository for `Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks`

jackpurcell/autoran-public

Automated framework for hijacking safety reasoning in large reasoning models via simulated reasoning traces and iterative prompt refinement to…

ragib-amin-nihal/pe-coa

Code Implementation of "Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models"

ryh1218/occ

Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling (ICME 2025)