Official code repository for the paper "Internal Activation as the Polar Star for Steering Unsafe LLM Behavior"
☆16May 31, 2026Updated 4 months ago
Alternatives and similar repositories for SafeSwitch
Users that are interested in SafeSwitch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Discover, evaluate, and intervene on circuits in transformer models.☆29Oct 8, 2026Updated 3 weeks ago
- Official code repository for the paper "ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind"☆27Sep 25, 2025Updated last year
- Official repo for "Binary Retrieval-augmented Reward Mitigates Hallucinations"☆16Nov 13, 2025Updated 11 months ago
- ☆21Apr 21, 2026Updated 6 months ago
- ☆13Jun 19, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [EMNLP 2025] AutoSteer: Automating Steering for Safe Multimodal Large Language Models☆16Aug 21, 2025Updated last year
- [WWW 2026 Oral] MoE-CL:Self-Evolving LLMs via Continual Instruction Tuning☆22Dec 1, 2025Updated 10 months ago
- Code for paper: "LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits"☆14Sep 19, 2025Updated last year
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆34Feb 26, 2025Updated last year
- Kelp is a novel plug-in framework that enables streaming risk detection within the LM generation pipeline.☆11Oct 20, 2025Updated last year
- ☆10Sep 9, 2024Updated 2 years ago
- UI-CTX: demystifying Android UI behaviors with a concise and effective representation, in NDSS '25☆14Jan 17, 2025Updated last year
- [ACL 2026] Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment☆14May 11, 2026Updated 5 months ago
- ☆10Jul 28, 2022Updated 4 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.
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated 2 years ago
- ☆24Nov 5, 2024Updated last year
- ICCV 2023 - AdaptGuard: Defending Against Universal Attacks for Model Adaptation☆11Dec 23, 2023Updated 2 years ago
- Offical repository for NeurIPS 2025 paper "From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monito…☆14May 5, 2026Updated 5 months ago
- [EMNLP 2025 Outstanding Paper Award] Official repo for DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph …☆22Nov 16, 2025Updated 11 months ago
- [CVPR 2023] "TrojViT: Trojan Insertion in Vision Transformers" by Mengxin Zheng, Qian Lou, Lei Jiang☆15Jan 5, 2024Updated 2 years ago
- ☆49Oct 1, 2024Updated 2 years ago
- Revisiting Cache Side-Channel Attacks in Deep Neural Networks Executables☆14Aug 27, 2024Updated 2 years ago
- Research on "Many-Shot Jailbreaking" in Large Language Models (LLMs). It unveils a novel technique capable of bypassing the safety mechan…☆19Aug 6, 2024Updated 2 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- This repository is the replication package of the NeurIPS19 paper "MarginGAN: Adversarial Training in Semi-Supervised Learning"☆12Oct 27, 2019Updated 7 years ago
- The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆19Mar 7, 2025Updated last year
- A Daemon for Real-Time Detection of Cache Side-Channel Attacks☆19Jun 21, 2026Updated 4 months ago
- ☆16Dec 11, 2025Updated 10 months ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆51Jun 1, 2026Updated 4 months ago
- ☆18Feb 22, 2025Updated last year
- The reinforcement learning codes for dataset SPA-VL☆48Jun 24, 2024Updated 2 years ago
- 智能医疗问诊系统 - LangGraph Agent + RAG + React☆25Jan 27, 2026Updated 9 months ago
- ☆12Jan 10, 2023Updated 3 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Jan 3, 2023Updated 3 years ago
- Overflow Prevention Enhances Long-Context Recurrent LLMs (COLM 2025)☆18Jul 8, 2025Updated last year
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆54Jul 15, 2025Updated last year
- Repository for the paper: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning☆18Feb 21, 2025Updated last year
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆123Updated this week
- A simple implementation of ReasonGenRM.☆19Apr 21, 2025Updated last year
- ☆18Oct 7, 2022Updated 4 years ago