RobustNLP / DeRTa
A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
☆52Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for DeRTa
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆96Updated 3 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆64Updated 8 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆83Updated 5 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆103Updated 3 weeks ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆60Updated last month
- Multilingual safety benchmark for Large Language Models☆22Updated 2 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆70Updated 6 months ago
- ☆153Updated 11 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆43Updated 11 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆69Updated 2 months ago
- ☆33Updated last year
- ☆86Updated 2 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆21Updated 4 months ago
- ☆31Updated 4 months ago
- ☆38Updated last week
- [Arxiv 2024] Adversarial attacks on multimodal agents☆37Updated 4 months ago
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated last month
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆55Updated 3 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆46Updated 3 months ago
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …☆35Updated 3 months ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆113Updated 7 months ago
- Python package for measuring memorization in LLMs.☆118Updated last month
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆120Updated 6 months ago
- A collection of automated evaluators for assessing jailbreak attempts.☆71Updated 4 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆71Updated 4 months ago
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆58Updated last month
- ☆38Updated last year
- ☆14Updated 2 weeks ago
- ☆49Updated last year
- ☆31Updated 9 months ago