git-disl / Safety-TaxLinks
This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".
☆18Updated 3 months ago
Alternatives and similar repositories for Safety-Tax
Users that are interested in Safety-Tax are comparing it to the libraries listed below
Sorting:
- ☆22Updated 3 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆44Updated 7 months ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆22Updated 9 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆46Updated 8 months ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆28Updated 3 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 5 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆79Updated 2 months ago
- ☆41Updated 8 months ago
- ☆20Updated 6 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 8 months ago
- SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆17Updated 2 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆134Updated 2 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆25Updated last year
- ☆35Updated 6 months ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆29Updated 7 months ago
- [ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"☆11Updated 3 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆55Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆55Updated 3 months ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 7 months ago
- ☆59Updated 11 months ago
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆27Updated 2 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆53Updated 10 months ago
- ☆30Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Updated this week
- [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models☆32Updated 6 months ago
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆32Updated 6 months ago
- ☆16Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆59Updated 8 months ago
- ☆27Updated 3 weeks ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL