Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
☆192Apr 23, 2025Updated last year
Alternatives and similar repositories for shallow-vs-deep-alignment
Users that are interested in shallow-vs-deep-alignment are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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
- Code for SafeMERGE (ACL 2026).☆15Oct 2, 2026Updated last week
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆91Mar 30, 2025Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated 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…☆359Feb 23, 2024Updated 2 years 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.
- ☆49Oct 1, 2024Updated 2 years ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆53Jan 15, 2026Updated 8 months ago
- A survey on harmful fine-tuning attack for large language model (ACM CSUR)☆248Sep 6, 2026Updated last month
- Improving Alignment and Robustness with Circuit Breakers☆270Sep 24, 2024Updated 2 years ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆43Mar 22, 2025Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆108May 20, 2025Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆356May 13, 2025Updated last year
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆687Apr 4, 2025Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆395Jan 23, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆283May 13, 2024Updated 2 years ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆456Jun 13, 2025Updated last year
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆1,062Aug 16, 2024Updated 2 years ago
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆18Apr 15, 2025Updated last year
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆90Feb 26, 2025Updated last year
- ☆24Dec 8, 2024Updated last year
- https://scale.com/research/mrt☆20Mar 16, 2026Updated 6 months ago
- NeurIPS'24 - LLM Safety Landscape☆41Oct 21, 2025Updated 11 months ago
- ☆25Jun 12, 2026Updated 3 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.
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆71Jun 9, 2025Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆87Mar 1, 2025Updated last year
- Official implementation for "ALI-Agent: Assessing LLMs'Alignment with Human Values via Agent-based Evaluation"☆21Jan 31, 2026Updated 8 months ago
- ☆49Sep 29, 2024Updated 2 years ago
- TACL 2025: Investigating Adversarial Trigger Transfer in Large Language Models☆20Aug 17, 2025Updated last year
- Accepted by IJCAI-24 Survey Track☆234Aug 25, 2024Updated 2 years ago
- ☆165Aug 11, 2025Updated last year
- An implementation of SEAL: Safety-Enhanced Aligned LLM fine-tuning via bilevel data selection.☆24Feb 20, 2025Updated last year
- ☆29Jun 5, 2024Updated 2 years 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.
- ☆71Jun 1, 2025Updated last year
- Official repo for "ProSec: Fortifying Code LLMs with Proactive Security Alignment"☆19Feb 26, 2026Updated 7 months ago
- ☆24Jun 13, 2024Updated 2 years ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated last year
- AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.☆251Apr 21, 2026Updated 5 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆85Oct 23, 2024Updated last year
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆29Oct 23, 2025Updated 11 months ago