DiagSafe: diagnostic LLM safety benchmark with prompt-level rubrics (3,489 bilingual prompts, 84-label taxonomy)
☆32Oct 26, 2026Updated this week
Alternatives and similar repositories for DiagSafe
Users that are interested in DiagSafe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Nov 19, 2025Updated 11 months ago
- Official implementation of the paper "AWM: Accurate Weight-Matrix Fingerprint for Large Language Models"☆13Feb 20, 2026Updated 8 months ago
- Kelp is a novel plug-in framework that enables streaming risk detection within the LM generation pipeline.☆11Oct 20, 2025Updated last year
- ☆13Jun 23, 2026Updated 4 months ago
- ☆13Jun 7, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 5 months ago
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆22Mar 22, 2026Updated 7 months ago
- 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
- [ICML 2026] Official implementations of ``SafeSearch: Automated Red-Teaming of LLM-Based Search Agents''☆20Mar 25, 2026Updated 7 months ago
- The official training code of SingProbe.☆36Sep 3, 2026Updated last month
- [ArXiv 2025] Imperceptible Jailbreaking against Large Language Models☆25Oct 7, 2025Updated last year
- [AAAI 2026] This is the official implementation of the paper "ExtendAttack: Attacking Servers of LRMs via Extending Reasoning".☆27Mar 18, 2026Updated 7 months ago
- ☆26Jun 18, 2025Updated last year
- 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.
- Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models☆11Mar 9, 2026Updated 7 months ago
- ☆27Dec 18, 2025Updated 10 months ago
- ☆20Aug 10, 2026Updated 2 months ago
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆33Sep 29, 2026Updated last month
- ☆27Jan 5, 2026Updated 9 months ago
- ☆15Mar 12, 2026Updated 7 months ago
- Evaluation Code@CoVEBench. Dual-level metrics.☆19Jul 4, 2026Updated 3 months ago
- We introduce ChatAnime, the first Emotionally Supportive Role-Playing (ESRP) dataset.☆14Oct 8, 2025Updated last year
- ☆10Oct 20, 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.
- CREST is a training-free test-time steering framework that discovers cognitive heads via simple offline calibration and then rotates acti…☆12Oct 22, 2026Updated last week
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆37Sep 30, 2026Updated last month
- CITETRACER: Cascading Multi-Agent for Citation Hallucination Detection☆14Updated this week
- ☆14Mar 10, 2025Updated last year
- Backdoor training and evaluation scripts for vision-language-action models on LIBERO.☆12Jul 25, 2026Updated 3 months ago
- Read and write Burp Suite Proxy HTTP history, byte for byte.☆30Aug 31, 2026Updated 2 months ago
- [ECCV 2026] The code repo of paper "HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task"☆15Jun 21, 2026Updated 4 months ago
- [ACL 2026] Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment☆14May 11, 2026Updated 5 months ago
- Explain emergent extreme events in LLM multi-agent systems. Shapley value attribution for When/Who/What drives Black Swans. EconAgent, Tw…☆18Mar 4, 2026Updated 7 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.
- [ACL-2026] Official codebase for "Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models". We int…☆17Aug 27, 2026Updated 2 months ago
- A runnable TypeScript tutorial that builds a minimal DeepSeek-style agent harness from scratch.☆14Aug 17, 2026Updated 2 months ago
- BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models☆16Updated this week
- Vstream - Video Analytics pipeline with Hardware based accelerations (dev - stage)☆10Feb 2, 2024Updated 2 years ago
- [ACL 2026] Official code and benchmark release for "Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation"☆15Jun 1, 2026Updated 4 months ago
- Awesome tools for interpreting, manipulating the internals of of deep neural networks.☆21Oct 13, 2026Updated 2 weeks ago
- ☆14Nov 17, 2025Updated 11 months ago