
ZORG-Jailbreak-Prompt-Text
Bypass restricted and censored content on AI chat prompts 😈

Bypass restricted and censored content on AI chat prompts 😈

During the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…

Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

AI / LLM Red Team Field Manual & Consultant’s Handbook

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

Red Team K8S Adversary Emulation Based on kubectl

Algorithms for outlier, adversarial and drift detection

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

Benchmark for evaluating AI agent safety against attacks embedded in skill-facing context, with 155 cases across 6 risk domains, measuring task…

Kernel-mode hook that intercepts, decrypts, and nullifies BEDaisy-to-service report traffic to suppress anti-cheat detection on UEFI and non-UEFI…

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

Spawns macOS programs through launchd's private XPC interface without execing them, making EDR record launchd as parent. Supports one-shot,…

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

The Security Toolkit for LLM Interactions

reverse engineering Gemini's SynthID detection

Adversary simulation and Red teaming platform with AI

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…