AI Security

mamadou-keita/deeclip

Implementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"

sleuthco/clawshield-public

Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF…

zhengxr930/maleval

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

albert-y1n/pismith

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

j-dahl7/mcp-attack-detection-sentinel

Sentinel detection lab for MCP attack chains: CVE-2026-26118 SSRF token theft, tool poisoning, cross-server exfiltration, identity post-exploitation.…

hannahxchen/llm-censorship-steering

Code for 'Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control'

jiamingzhang94/unlearnable-clusters

CVPR2023: Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples

microsoft/fides

Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.

knoveleng/redeval

[ICLR 2026] - Official repo for the paper: "RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models"

livecvebench/cve-factory

CVE-Factory

franz-chang/adaptive_greedy_local_search

AGLS

nishitvp/better_opts_attacks

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

knostic/openant

OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery product, helping defenders proactively find verified security flaws…

pasquini-dario/project_mantis

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

q-rz/saffron

Inference scaling for LLM safety assurance

sbamit/exponentiated-gradient-descent-llm-attack

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.