[EMNLP 2025] Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
☆12Aug 22, 2025Updated last year
Alternatives and similar repositories for Reasoning-to-Defend
Users that are interested in Reasoning-to-Defend are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Accepted by ICLR 2026☆10Jun 9, 2026Updated 5 months ago
- [NDSS'25] The official implementation of safety misalignment.☆20Jan 8, 2025Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆40Jan 17, 2025Updated last year
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆84Updated this week
- ☆25Feb 17, 2026Updated 9 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.
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated 4 months ago
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- ☆20Jun 4, 2024Updated 2 years ago
- [ICLR 2025] Code implementation of R^2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning☆24Jul 8, 2024Updated 2 years ago
- [EMNLP 2025] AutoSteer: Automating Steering for Safe Multimodal Large Language Models☆16Aug 21, 2025Updated last year
- An implementation for MLLM oversensitivity evaluation☆18Nov 16, 2024Updated 2 years ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆92Feb 26, 2025Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated 2 years ago
- ☆54Jul 12, 2026Updated 4 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆66Sep 5, 2025Updated last year
- Turn every moment into momentum☆22Jun 1, 2026Updated 5 months ago
- ☆123Apr 27, 2025Updated last year
- Code for ACL 2025 accepted paper titled "MPO: Multilingual Safety Alignment via Reward Gap Optimization"☆12Jun 5, 2025Updated last year
- A Review of Deep-Learning-based Singing Voice Synthesis Approaches☆13Oct 3, 2026Updated last month
- ☆27Mar 17, 2025Updated last year
- ☆13Aug 24, 2024Updated 2 years ago
- [EMNLP 2024] ”ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models“☆27Jun 24, 2024Updated 2 years ago
- Risk-Sensitive GRPO algorithm (ICLR2026)☆14Sep 30, 2025Updated last year
- 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.
- Adversarial Attack for Pre-trained Code Models☆10Jul 19, 2022Updated 4 years ago
- ☆30Aug 12, 2026Updated 3 months ago
- ☆33Jun 24, 2024Updated 2 years ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆91Mar 30, 2025Updated last year
- ☆31May 14, 2025Updated last year
- Official implementation of "AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery".☆13Aug 11, 2025Updated last year
- ☆15Jun 13, 2025Updated last year
- ☆12Jan 13, 2026Updated 10 months ago
- Code for the paper "AsFT: Anchoring Safety During LLM Fune-Tuning Within Narrow Safety Basin".☆39Jul 10, 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.
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆38Jun 23, 2025Updated last year
- ☆12Feb 5, 2025Updated last year
- Code for Personalized Large Language Models via Selective Prompt Tuning☆10Jun 26, 2024Updated 2 years ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆89Nov 3, 2024Updated 2 years ago
- The official source code for "Single-cell RNA-seq data imputation using Bi-level Feature Propagation", accepted at Briefings in Bioinform…☆10May 9, 2024Updated 2 years ago
- ☆17Oct 22, 2022Updated 4 years ago
- ☆20Jun 17, 2024Updated 2 years ago
Are these results useful?