LLMSecurity / MasterKey
MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks and evaluating their defenses.
☆10Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for MasterKey
- ☆18Updated last month
- ☆13Updated 3 months ago
- Composite Backdoor Attacks Against Large Language Models☆9Updated 7 months ago
- ☆19Updated 4 months ago
- ☆17Updated 2 years ago
- ☆73Updated 7 months ago
- A toolbox for backdoor attacks.☆19Updated last year
- ☆18Updated last year
- ☆12Updated 3 weeks ago
- ☆14Updated 11 months ago
- Repository for Towards Codable Watermarking for Large Language Models☆29Updated last year
- Code to generate NeuralExecs (prompt injection for LLMs)☆17Updated 3 months ago
- Invisible Backdoor Attack with Sample-Specific Triggers☆91Updated 2 years ago
- 😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.☆133Updated last week
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆31Updated 8 months ago
- ☆11Updated 11 months ago
- multi-bit language model watermarking (NAACL 24)☆11Updated 2 months ago
- A curated list of papers & resources on backdoor attacks and defenses in deep learning.☆178Updated 8 months ago
- ☆9Updated 2 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆17Updated last year
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆11Updated 9 months ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆113Updated last week
- 复现了下Neural Cleanse这篇论文,真的是简单而有效,发在了okaland☆30Updated 3 years ago
- [USENIX Scurity'24] REMARK-LLM: A robust and efficient watermarking framework for generative large language models☆18Updated 3 weeks ago
- ☆39Updated 9 months ago
- ☆37Updated 3 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆20Updated last year
- Official Repo of ICLR 24 BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆17Updated 3 months ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆37Updated 2 years ago
- A list of recent papers about adversarial learning☆74Updated this week