code space of paper "Safety Layers in Aligned Large Language Models: The Key to LLM Security" (ICLR 2025)
☆25Apr 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)☆29Sep 10, 2024Updated last year
- [EMNLP 2025] Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment☆16Jul 22, 2025Updated last year
- DSN jailbreak Attack & Evaluation Ensemble☆17Feb 7, 2026Updated 6 months ago
- ☆46Jan 15, 2025Updated last year
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆18Jan 14, 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.
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆29Dec 21, 2025Updated 7 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☆40Oct 21, 2025Updated 9 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated 10 months ago
- [EMNLP 2025] Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking☆12Aug 22, 2025Updated 11 months ago
- ☆19Dec 23, 2025Updated 7 months ago
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆30Jan 29, 2026Updated 6 months ago
- [AAAI-2026]MAJIC: Markovian Adaptive Jailbreaking. An automated black-box attack framework against LLMs that iteratively selects and fuse…☆17Jul 25, 2026Updated 3 weeks ago
- [CVPR'26] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization☆22Feb 19, 2026Updated 5 months ago
- 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.
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?" [AAAI'26]☆21Dec 26, 2025Updated 7 months ago
- [EMNLP 2025] AutoSteer: Automating Steering for Safe Multimodal Large Language Models☆16Aug 21, 2025Updated 11 months ago
- Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"☆35Dec 6, 2024Updated last year
- A survey on harmful fine-tuning attack for large language model (ACM CSUR)☆246Jun 22, 2026Updated last month
- ☆31Mar 11, 2026Updated 5 months ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 2 months ago
- Code for paper: "PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification", IEEE S&P 2024.☆35Aug 10, 2024Updated 2 years ago
- ☆61Jun 5, 2024Updated 2 years ago
- ☆24Dec 8, 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.
- 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 last year
- ☆42Jul 3, 2026Updated last month
- ☆23May 14, 2025Updated last year
- 微芒虚拟区块链操作系统☆18Mar 2, 2023Updated 3 years ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆91Mar 30, 2025Updated last year
- 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
- code for infocom 2021 paper MANDA☆11May 30, 2023Updated 3 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.
- Toolkit to benchmark the tamper-resistance of LLMs.☆28May 15, 2026Updated 3 months ago
- 🌿快速生成文件夹目录结构，支持定义目录层级，支持生成到 markdown 文件。☆13Oct 19, 2022Updated 3 years ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆90May 2, 2025Updated last year
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆29Oct 23, 2025Updated 9 months ago
- 使用Transformer进行中英翻译（demo）☆17Aug 25, 2023Updated 2 years ago
- ☆25Mar 30, 2026Updated 4 months ago
- Official implementation of Visco-Attack (EMNLP 2025 Main). An open-source one-click reproduction script is also provided.☆31Apr 11, 2026Updated 4 months ago