bboylyg / BackdoorLLM
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models
☆114Updated 3 weeks ago
Alternatives and similar repositories for BackdoorLLM:
Users that are interested in BackdoorLLM are comparing it to the libraries listed below
- [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models☆30Updated 7 months ago
- [USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models☆126Updated 3 weeks ago
- ☆51Updated 3 months ago
- ☆25Updated 5 months ago
- A list of recent papers about adversarial learning☆125Updated this week
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆121Updated 3 weeks ago
- Composite Backdoor Attacks Against Large Language Models☆12Updated 11 months ago
- ☆119Updated 6 months ago
- Agent Security Bench (ASB)☆64Updated last week
- A curated list of trustworthy Generative AI papers. Daily updating...☆70Updated 6 months ago
- ☆20Updated last year
- ☆78Updated last month
- TAP: An automated jailbreaking method for black-box LLMs☆150Updated 3 months ago
- ☆42Updated 2 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆63Updated 5 months ago
- [NDSS'25 Poster] A collection of automated evaluators for assessing jailbreak attempts.☆122Updated last week
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆48Updated 6 months ago
- ☆27Updated 5 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆24Updated last year
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆102Updated last month
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆55Updated 3 months ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 7 months ago
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆173Updated last year
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆35Updated last year
- Code to generate NeuralExecs (prompt injection for LLMs)☆20Updated 3 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆30Updated last year
- Red Queen Dataset and data generation template☆12Updated 5 months ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆135Updated last year