Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"
☆20Oct 26, 2023Updated 2 years ago
Alternatives and similar repositories for Self-Reminder-Data
Users that are interested in Self-Reminder-Data are comparing it to the libraries listed below
Sorting:
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆56Nov 13, 2023Updated 2 years ago
- The python implementation of our "UA-FedRec: Untargeted Attack on Federated News Recommendation" in KDD 2023.☆19Aug 2, 2022Updated 3 years ago
- ☆51Aug 10, 2024Updated last year
- Implementation for the paper "Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning"☆11Jan 10, 2025Updated last year
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆24May 20, 2025Updated 9 months ago
- ☆25Mar 16, 2025Updated 11 months ago
- ☆21Aug 30, 2025Updated 6 months ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?"☆21Dec 26, 2025Updated 2 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆26Oct 24, 2024Updated last year
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated 9 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆61Aug 8, 2024Updated last year
- ☆26Dec 14, 2021Updated 4 years ago
- [TMLR 2025] On Memorization in Diffusion Models☆31Oct 5, 2023Updated 2 years ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆25Feb 16, 2026Updated 2 weeks ago
- 本文提出了一个基于“文心一言”的中国LLMs的安全评估基准，其中包括8种典型的安全场景和6种指令攻击类型。此外，本文还提出了安全评估的框架和过程，利用手动编写和收集开源数据的测试Prompts，以及人工干预结合利用LLM强大的评估能力作为“共同评估者”。☆33Sep 1, 2023Updated 2 years ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆69Oct 23, 2024Updated last year
- ☆197Nov 26, 2023Updated 2 years ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆34Nov 8, 2024Updated last year
- ☆11Dec 23, 2024Updated last year
- Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)☆142Apr 7, 2025Updated 11 months ago
- ☆34May 9, 2025Updated 9 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆151Jul 19, 2024Updated last year
- LLM Self Defense: By Self Examination, LLMs know they are being tricked☆51May 21, 2024Updated last year
- [CVPR2025] Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters☆43Mar 11, 2025Updated 11 months ago
- DreamSmooth: Improving Model-Based RL with Reward Smoothing (ICLR 2024)☆12May 6, 2024Updated last year
- A repository for resources relating to NLP in the Balochi language☆19Jun 3, 2023Updated 2 years ago
- Residual Quantization Autoencoder, used for interpreting LLMs☆14Jan 1, 2025Updated last year
- A collection of heat engines, based on the OpenAI Gym environment framework for use with reinforcement learning applications.☆15Dec 20, 2021Updated 4 years ago
- ☆11Jun 7, 2023Updated 2 years ago
- On the Robustness of GUI Grounding Models Against Image Attacks☆12Apr 8, 2025Updated 10 months ago
- code for polite☆11Feb 28, 2024Updated 2 years ago
- ☆10Jul 13, 2024Updated last year
- ☆16Feb 22, 2025Updated last year
- Curated list of awesome datasets for various table understanding tasks☆18Sep 5, 2025Updated 6 months ago
- ☆11Jan 11, 2022Updated 4 years ago
- About Code release for "Imagination Mechanism: Mesh Information Propagation for Enhancing Data Efficiency in Reinforcement Learning"☆13Oct 7, 2023Updated 2 years ago
- The code for the paper "A Bayesian Approach to Online Planning" published in ICML 2024.☆13Jun 17, 2024Updated last year
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆52Jul 15, 2025Updated 7 months ago
- Debiasing Through Data Attribution☆12May 23, 2024Updated last year