microsoft / BIPIALinks
A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.
☆77Updated last year
Alternatives and similar repositories for BIPIA
Users that are interested in BIPIA are comparing it to the libraries listed below
Sorting:
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆239Updated 2 weeks ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆167Updated 4 months ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆64Updated 2 weeks ago
- ☆71Updated last year
- TAP: An automated jailbreaking method for black-box LLMs☆182Updated 8 months ago
- This repository provides a benchmark for prompt Injection attacks and defenses☆264Updated last month
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆165Updated 8 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆54Updated 10 months ago
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆91Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆333Updated 7 months ago
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆66Updated last month
- Code to generate NeuralExecs (prompt injection for LLMs)☆22Updated 9 months ago
- Papers about red teaming LLMs and Multimodal models.☆134Updated 2 months ago
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆270Updated 3 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆141Updated 4 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆54Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆89Updated 10 months ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆400Updated 4 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆140Updated last year
- ☆60Updated 8 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆144Updated 8 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆182Updated 6 months ago
- ☆85Updated 9 months ago
- Agent Security Bench (ASB)☆107Updated 2 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆159Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆317Updated last year
- ☆91Updated last year
- ☆599Updated last month
- A Comprehensive Assessment of Trustworthiness in GPT Models☆302Updated 11 months ago
- The automated prompt injection framework for LLM-integrated applications.☆221Updated 11 months ago