RenatoGeh / advtokLinks
Adversarial Tokenization
☆29Updated last month
Alternatives and similar repositories for advtok
Users that are interested in advtok are comparing it to the libraries listed below
Sorting:
- General research for Dreadnode☆25Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆91Updated last year
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…☆42Updated 7 months ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆114Updated last year
- Source code of "TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification", ACL2024 (findings)☆13Updated 10 months ago
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆140Updated 9 months ago
- ☆68Updated 2 months ago
- ☆89Updated 10 months ago
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆16Updated last year
- [EMNLP 2024] Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction☆17Updated 10 months ago
- Papers about red teaming LLMs and Multimodal models.☆140Updated 4 months ago
- ☆80Updated last year
- ☆17Updated last year
- An interactive CLI application for interacting with authenticated Jupyter instances.☆55Updated 5 months ago
- Minimal workflows☆20Updated last year
- Nemesis agent for Mythic☆27Updated last year
- Remote code execution in Power Platform connectors via JSON deserialization☆23Updated 2 years ago
- using ML models for red teaming☆44Updated 2 years ago
- ☆92Updated last year
- Configurable, Community driven, HTTP C2 Profile☆26Updated 4 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆166Updated 9 months ago
- Putting the C2 in C2loudflare☆16Updated last year
- Example agents for the Dreadnode platform☆17Updated 2 months ago
- Attack to induce LLMs within hallucinations☆157Updated last year
- Entra ID Password Protection Banned Password Lists☆16Updated last year
- AWSDoor is a red team automation tool designed to simulate advanced attacker behavior in AWS environments☆26Updated 3 weeks ago
- Ansible role that Installs Mythic☆18Updated last year
- ☆58Updated this week
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆64Updated this week
- ☆19Updated last year