Reapor-Yurnero / imprompter
Codebase of https://arxiv.org/abs/2410.14923
☆30Updated last month
Related projects ⓘ
Alternatives and complementary repositories for imprompter
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆48Updated this week
- Red-Teaming Language Models with DSPy☆142Updated 7 months ago
- Do you want to learn AI Security but don't know where to start ? Take a look at this map.☆19Updated 6 months ago
- Thorn in a HaizeStack test for evaluating long-context adversarial robustness.☆26Updated 3 months ago
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆47Updated 7 months ago
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆195Updated 8 months ago
- A prompt injection game to collect data for robust ML research☆44Updated last month
- A benchmark for prompt injection detection systems.☆87Updated 2 months ago
- BlindBox is a tool to isolate and deploy applications inside Trusted Execution Environments for privacy-by-design apps☆57Updated last year
- Research on "Many-Shot Jailbreaking" in Large Language Models (LLMs). It unveils a novel technique capable of bypassing the safety mechan…☆18Updated 7 months ago
- Scrape details about Code Interpreter to track any changes☆43Updated 2 weeks ago
- A tool for testing the efficacy of prompts and prompt + model combinations.☆59Updated 3 months ago
- Payloads for Attacking Large Language Models☆64Updated 4 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆86Updated 5 months ago
- Lightweight LLM Interaction Framework☆210Updated this week
- ☆63Updated this week
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]☆220Updated 2 months ago
- ☆20Updated this week
- PII Masker is an open-source tool for protecting sensitive data by automatically detecting and masking PII using advanced AI, powered by …☆41Updated this week
- The Privacy Adversarial Framework (PAF) is a knowledge base of privacy-focused adversarial tactics and techniques. PAF is heavily inspire…☆54Updated last year
- A steganography tool for automatically encoding images that act as prompt injections/jailbreaks for AIs with code interpreter and vision.☆39Updated last month
- Accompanying code and SEP dataset for the "Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?" paper.☆44Updated 5 months ago
- Learn about a type of vulnerability that specifically targets machine learning models☆183Updated 5 months ago
- Sphynx Hallucination Induction☆48Updated 3 months ago
- Dropbox LLM Security research code and results☆217Updated 6 months ago
- ☆15Updated last week
- A collection of awesome resources related AI security☆131Updated 8 months ago
- ☆29Updated 3 weeks ago
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆84Updated 8 months ago
- Fiddler Auditor is a tool to evaluate language models.☆171Updated 8 months ago