LostOxygen / llm-confidentialityLinks
Whispers in the Machine: Confidentiality in Agentic Systems
☆41Updated 3 weeks ago
Alternatives and similar repositories for llm-confidentiality
Users that are interested in llm-confidentiality are comparing it to the libraries listed below
Sorting:
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆373Updated 2 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆178Updated 9 months ago
- LLM security and privacy☆53Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆371Updated 11 months ago
- PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to a…☆447Updated last year
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆55Updated last year
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆78Updated 5 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆184Updated 8 months ago
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆112Updated last year
- A prompt injection game to collect data for robust ML research☆65Updated 11 months ago
- ☆75Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆92Updated last year
- Agent Security Bench (ASB)☆167Updated 2 months ago
- Papers about red teaming LLMs and Multimodal models.☆159Updated 7 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆213Updated last year
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆346Updated 2 months ago
- ☆112Updated last month
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆393Updated last month
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆150Updated 4 months ago
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆63Updated 7 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆67Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆176Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆78Updated 4 months ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆62Updated last month
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆48Updated last year
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆101Updated 11 months ago
- ☆159Updated last year
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆73Updated 7 months ago