code space of paper "Safety Layers in Aligned Large Language Models: The Key to LLM Security" (ICLR 2025)
☆26Apr 26, 2025Updated last year
Alternatives and similar repositories for Safety-Layers
Users that are interested in Safety-Layers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆28Sep 10, 2024Updated 2 years ago
- [EMNLP 2025] Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment☆17Jul 22, 2025Updated last year
- DSN jailbreak Attack & Evaluation Ensemble☆17Feb 7, 2026Updated 7 months ago
- ☆47Jan 15, 2025Updated last year
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆18Jan 14, 2025Updated 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.
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆30Dec 21, 2025Updated 9 months ago
- An implementation of SEAL: Safety-Enhanced Aligned LLM fine-tuning via bilevel data selection.☆24Feb 20, 2025Updated last year
- NeurIPS'24 - LLM Safety Landscape☆41Oct 21, 2025Updated 11 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated last year
- [EMNLP 2025] Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking☆12Aug 22, 2025Updated last year
- ☆19Dec 23, 2025Updated 9 months ago
- [CVPR'26] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization☆23Feb 19, 2026Updated 7 months ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?" [AAAI'26]☆21Dec 26, 2025Updated 8 months ago
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"☆35Dec 6, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆19Jun 29, 2025Updated last year
- A survey on harmful fine-tuning attack for large language model (ACM CSUR)☆248Sep 6, 2026Updated 2 weeks ago
- ☆31Mar 11, 2026Updated 6 months ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 3 months ago
- ☆62Jun 5, 2024Updated 2 years ago
- ☆24Dec 8, 2024Updated last year
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆35Aug 10, 2024Updated 2 years ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆89Feb 26, 2025Updated last year
- All code and data necessary to replicate experiments in the paper BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Model…☆13Sep 16, 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.
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆91Mar 30, 2025Updated last year
- ☆27May 14, 2025Updated last year
- 微芒虚拟区块链操作系统☆17Mar 2, 2023Updated 3 years ago
- Restore safety in fine-tuned language models through task arithmetic☆33Mar 28, 2024Updated 2 years ago
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆91May 2, 2025Updated last year
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆29Oct 23, 2025Updated 11 months ago
- 使用Transformer进行中英翻译（demo）☆17Aug 25, 2023Updated 3 years ago
- ☆25Mar 30, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Official implementation of Visco-Attack (EMNLP 2025 Main). An open-source one-click reproduction script is also provided.☆31Apr 11, 2026Updated 5 months ago
- ☆19Feb 26, 2024Updated 2 years ago
- ☆21Nov 13, 2023Updated 2 years ago
- Create a LangChain ReAct agent with multiple tools (Python REPL and DuckDuckGo Search)☆15Updated this week
- ☆49Oct 1, 2024Updated last year
- A collection of cross-platform social media posts about the 2022 U.S. midterm elections☆13Sep 20, 2024Updated 2 years ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆37Oct 15, 2023Updated 2 years ago