Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"
☆27Jul 6, 2024Updated 2 years ago
Alternatives and similar repositories for virtual-prompt-injection
Users that are interested in virtual-prompt-injection are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for the paper "Exploring Backdoor Vulnerabilities of Chat Models"☆19Apr 13, 2024Updated 2 years ago
- ☆61May 30, 2024Updated 2 years ago
- ICL backdoor attack☆17Nov 4, 2024Updated 2 years ago
- ☆13Sep 8, 2024Updated 2 years ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆119Sep 27, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆11Oct 3, 2021Updated 5 years ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆61Apr 8, 2024Updated 2 years ago
- Working Memory Attack on LLMs☆18May 27, 2025Updated last year
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆15Jun 21, 2024Updated 2 years ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆25Mar 23, 2024Updated 2 years ago
- ☆39Oct 17, 2024Updated 2 years ago
- ☆18Jul 1, 2021Updated 5 years ago
- ☆27Jun 27, 2024Updated 2 years ago
- ☆23Sep 2, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆621Jul 4, 2025Updated last year
- [USENIX Security'24] REMARK-LLM: A robust and efficient watermarking framework for generative large language models☆28Oct 23, 2024Updated 2 years ago
- ☆33Sep 3, 2024Updated 2 years ago
- Evaluating Durability: Benchmark Insights into Multimodal Watermarking☆12Jun 7, 2024Updated 2 years ago
- Code for paper: "RemovalNet: DNN model fingerprinting removal attack", IEEE TDSC 2023.☆10Nov 27, 2023Updated 2 years ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?" [AAAI'26]☆21Dec 26, 2025Updated 10 months ago
- ☆34Aug 11, 2022Updated 4 years ago
- ☆25Jan 17, 2025Updated last year
- A challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems, Co-located with EMNLP2022 SereTOD Workshop☆26Oct 1, 2022Updated 4 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- [CIKM 2024] Trojan Activation Attack: Attack Large Language Models using Activation Steering for Safety-Alignment.☆30Jul 29, 2024Updated 2 years ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆68Apr 24, 2024Updated 2 years ago
- Watermarking LLM papers up-to-date☆12Dec 17, 2023Updated 2 years ago
- Implementation of CVPR 2022 paper "Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations"☆11Apr 1, 2024Updated 2 years ago
- [AAAI 2025] Security Attacks on LLM-based Code Completion Tools☆23Dec 31, 2025Updated 10 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆152Jul 19, 2024Updated 2 years ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆71Feb 5, 2024Updated 2 years ago
- Re-thinking Federated Active Learning based on Inter-class Diversity (CVPR 2023)☆32May 31, 2023Updated 3 years ago
- Official implementation of "AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery".☆13Aug 11, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Python code to automatically produce a summary of a piece of text.☆11Sep 8, 2016Updated 10 years ago
- ☆11Apr 17, 2023Updated 3 years ago
- ☆18Oct 7, 2022Updated 4 years ago
- BrainWash: A Poisoning Attack to Forget in Continual Learning☆13Apr 15, 2024Updated 2 years ago
- Target Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning☆10Jul 2, 2019Updated 7 years ago
- ☆11Jun 12, 2023Updated 3 years ago
- Jekyll theme for displaying a resume/cv in a clean, minimallistic way.☆10Jan 4, 2021Updated 5 years ago
Are these results useful?