DARWIN is a self-evolving LLM jailbreak framework that grows a reusable strategy pool through external extraction, sandbox filtering, history-memory retrieval, Markov-based strategy selection, and reflective/genetic evolution.
☆90Sep 28, 2026Updated last month
Alternatives and similar repositories for DARWIN
Users that are interested in DARWIN are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [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
- ☆15Apr 1, 2026Updated 7 months ago
- A prototype for innovative BGP anomaly detection system --- BGPShield.☆18Apr 7, 2026Updated 7 months ago
- TRACE is an agentic jailbreaking framework that can reduce attack difficulty, induce the agent to execute end-to-end attack workflows thr…☆41Oct 1, 2026Updated last month
- ICLR 206☆15Aug 18, 2026Updated 2 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.
- Two text jailbreak attacks against commercial black-box LLMs and a malicious content detection method, the latter of which is applied to …☆12Oct 21, 2026Updated 3 weeks ago
- Source code and scripts for the paper "Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks"☆20Dec 10, 2024Updated last year
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆80May 8, 2026Updated 6 months ago
- [ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang☆16May 4, 2023Updated 3 years ago
- 🚀 Automated & lossless LaTeX paper migration tool. Instantly convert your Overleaf source between top-tier AI conference templates (Neur…☆238Apr 8, 2026Updated 7 months ago
- ☆40Oct 15, 2026Updated last month
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- Official implementation of "Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference" (NDSS 2026)☆23Feb 28, 2026Updated 8 months ago
- Paper list of LLM fingerprinting, based on our paper titled "SoK: Large Language Model Copyright Auditing via Fingerprinting".☆36Aug 28, 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.
- Code for paper "JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills."☆31Sep 3, 2026Updated 2 months ago
- [ICLR 2026] Monitoring Decomposition Attacks with Lightweight Sequential Monitors☆12Apr 20, 2026Updated 6 months ago
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆15Dec 16, 2024Updated last year
- ☆36Apr 13, 2026Updated 7 months ago
- ☆10Oct 7, 2026Updated last month
- [WWW 2026 Oral] Official code for our paper "Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gr…☆13Jan 21, 2026Updated 9 months ago
- SHE: Trajectory-driven Safety Harness Evolution for LLM Agents☆24Aug 4, 2026Updated 3 months ago
- ☆57Feb 25, 2026Updated 8 months ago
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 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.
- Official implementation of "HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety"☆22Aug 19, 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
- Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"☆60Oct 15, 2026Updated last month
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆25May 20, 2025Updated last year
- Official Code for Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification.☆22Jul 1, 2026Updated 4 months ago
- Official code for our paper "SoK: Large Language Model Copyright Auditing via Fingerprinting"☆20Dec 31, 2025Updated 10 months ago
- [NeurIPS 2025] Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack☆17Nov 19, 2025Updated 11 months ago
- open Source code for propensity evaluation☆22Apr 25, 2026Updated 6 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22May 6, 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.
- [TDSC 2024] Official code for our paper "FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model"☆23May 14, 2025Updated last year
- ☆16May 5, 2026Updated 6 months ago
- TRACE, a framework for turn-aware credit assignment for multi-turn jailbreak optimization☆22Aug 26, 2026Updated 2 months ago
- The Strata-Sword is a hierarchical Chinese-English jailbreak safety benchmark based on quantified reasoning complexity, developed in-hous…☆21Sep 3, 2025Updated last year
- ☆12May 6, 2022Updated 4 years ago
- ☆229Aug 17, 2025Updated last year
- “ToolHazard: Scalable Red Teaming of LLM Agents via Adversarial Tool-Interactive Environment and Task Synthesis”☆15Aug 18, 2026Updated 2 months ago
Are these results useful?