wagner-group / prompt-injection-defenseLinks
Fine-tuning base models to build robust task-specific models
☆31Updated last year
Alternatives and similar repositories for prompt-injection-defense
Users that are interested in prompt-injection-defense are comparing it to the libraries listed below
Sorting:
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆89Updated 11 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆141Updated 4 months ago
- ☆71Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆54Updated 10 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆95Updated 7 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆46Updated last month
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆66Updated last month
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆144Updated 9 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆161Updated last year
- ☆22Updated last year
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆43Updated last year
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆48Updated last month
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆17Updated last year
- ☆100Updated 6 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆167Updated 4 months ago
- ☆181Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆71Updated 9 months ago
- ☆20Updated 3 months ago
- Code to generate NeuralExecs (prompt injection for LLMs)☆22Updated 9 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆60Updated 5 months ago
- ☆45Updated last year
- TAP: An automated jailbreaking method for black-box LLMs☆182Updated 8 months ago
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆27Updated last year
- ☆39Updated 9 months ago
- ☆60Updated 8 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆58Updated last year
- Agent Security Bench (ASB)☆108Updated 2 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆182Updated 6 months ago
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆99Updated 6 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆55Updated last year