[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
☆111Aug 7, 2024Updated last year
Alternatives and similar repositories for LLM-Conversation-Safety
Users that are interested in LLM-Conversation-Safety are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide…☆1,848May 8, 2026Updated last week
- Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confid…☆23May 8, 2023Updated 3 years ago
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆21Mar 25, 2024Updated 2 years ago
- [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!☆39Aug 2, 2024Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆350Feb 23, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆593Apr 4, 2025Updated last year
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆19Aug 22, 2024Updated last year
- ☆54Dec 24, 2024Updated last year
- LiveSecBench：动态中文大模型安全榜单☆28Mar 9, 2026Updated 2 months ago
- ☆732Jul 2, 2025Updated 10 months ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆325Jun 7, 2024Updated last year
- A Domain-Specific Language, Jailbreak Attack Synthesizer and Dynamic LLM Redteaming Toolkit☆27Dec 5, 2024Updated last year
- ☆24Dec 8, 2024Updated last year
- ☆77Jan 21, 2026Updated 3 months ago
- 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.
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆386Jan 23, 2025Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆111Mar 8, 2024Updated 2 years ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆72May 22, 2025Updated 11 months ago
- Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents☆76May 8, 2026Updated last week
- Papers and resources related to the security and privacy of LLMs 🤖☆577Jun 8, 2025Updated 11 months ago
- ☆19Oct 2, 2023Updated 2 years ago
- Universal and Transferable Attacks on Aligned Language Models☆4,661Aug 2, 2024Updated last year
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆37Apr 8, 2026Updated last month
- ICCV 2023 - AdaptGuard: Defending Against Universal Attacks for Model Adaptation☆11Dec 23, 2023Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆162Nov 30, 2024Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆104Mar 7, 2024Updated 2 years ago
- ☆169Sep 2, 2024Updated last year
- ☆20Oct 28, 2025Updated 6 months ago
- An easy-to-use Python framework to generate adversarial jailbreak prompts.☆853Mar 30, 2026Updated last month
- [ICML 2024] TrustLLM: Trustworthiness in Large Language Models☆625Jun 24, 2025Updated 10 months ago
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆443Jan 22, 2025Updated last year
- ☆13Jun 17, 2024Updated last year
- ☆60Jun 13, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆16Apr 27, 2024Updated 2 years ago
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆287Jul 28, 2025Updated 9 months ago
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆26Jun 17, 2025Updated 11 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆103Jan 11, 2026Updated 4 months ago
- ☆11Oct 3, 2021Updated 4 years ago
- code released for our TIP 2021 paper "Adversarial Domain Adaptation with Prototype-based Normalized Output Conditioner"☆15May 24, 2023Updated 2 years ago
- [ICLR2023] Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning (https://arxiv.org/abs/2210.0022…☆39Jan 30, 2023Updated 3 years ago