[AAAI-2026]MAJIC: Markovian Adaptive Jailbreaking. An automated black-box attack framework against LLMs that iteratively selects and fuses innovative disguise strategies guided by a dynamically updated Markov transition matrix.
☆20Jul 25, 2026Updated 3 months ago
Alternatives and similar repositories for MAJIC-AAAI2026
Users that are interested in MAJIC-AAAI2026 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Apr 1, 2026Updated 7 months ago
- A prototype for innovative BGP anomaly detection system --- BGPShield.☆18Apr 7, 2026Updated 7 months ago
- ☆14Jul 29, 2026Updated 3 months ago
- [NDSS 2026] DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization☆13Dec 17, 2025Updated 11 months ago
- [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
- 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.
- DARWIN is a self-evolving LLM jailbreak framework that grows a reusable strategy pool through external extraction, sandbox filtering, his…☆90Sep 28, 2026Updated last month
- 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
- [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
- Code for paper "JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills."☆32Sep 3, 2026Updated 2 months ago
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- [ICLR 2026] Monitoring Decomposition Attacks with Lightweight Sequential Monitors☆12Apr 20, 2026Updated 6 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
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion (NeurIPS 2024 Spotlight)☆14Mar 31, 2025Updated last year
- ☆229Aug 17, 2025Updated last year
- We introduce a novel approach for Autonomous System (AS) embedding using deep learning based on only BGP announcements. Using these vecto…☆11Oct 25, 2023Updated 3 years ago
- ☆16Jul 15, 2025Updated last year
- code space of paper "Safety Layers in Aligned Large Language Models: The Key to LLM Security" (ICLR 2025)☆27Apr 26, 2025Updated last year
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆31Jan 29, 2026Updated 9 months ago
- NeurIPS'24 - LLM Safety Landscape☆41Oct 21, 2025Updated last year
- Agent skill (Claude Code / Codex) for condensing, typesetting and fact-checking a LaTeX paper to ICASSP's 4+1 page limit, verified by mea…☆19Sep 14, 2026Updated 2 months ago
- Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs☆12Nov 7, 2024Updated 2 years ago
- 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.
- ☆48Feb 8, 2025Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆37Oct 15, 2023Updated 3 years ago
- Academic Writing Style Guide for Programmers, compiled from Writing in the Sciences by Stanford University.☆22Feb 3, 2021Updated 5 years ago
- ☆11Jan 21, 2021Updated 5 years ago
- Official implementation of "Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference" (NDSS 2026)☆23Updated this week
- Host CIFAR-10.2 Data Set☆13Sep 22, 2021Updated 5 years ago
- [NAACL 2022] "SemAttack: Natural Textual Attacks via Different Semantic Spaces" by Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li☆21Jun 11, 2022Updated 4 years ago
- [ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"☆11Feb 20, 2025Updated last year
- Additional material for paper Profiling BGP Serial Hijackers: Capturing Persistent Misbehavior in the Global Routing Table, IMC ’19☆10Mar 24, 2021Updated 5 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- TRACE, a framework for turn-aware credit assignment for multi-turn jailbreak optimization☆22Aug 26, 2026Updated 2 months ago
- Official Pytorch implementation for our ACM MM 2023 paper: Moiré Backdoor Attack (MBA): A Novel Trigger for Pedestrian Detectors in the P…☆16Jan 22, 2024Updated 2 years ago
- Paper of AI Agent Security☆10Sep 10, 2025Updated last year
- 面向 codex 的西安电子科技大学本科毕业设计(论文)辅助 skill☆20May 23, 2026Updated 5 months ago
- Test for Graph Unlearning Benchmark☆22Jul 12, 2025Updated last year
- ☆10Jan 29, 2026Updated 9 months ago
- Official Implementation of implicit reference attack☆11Oct 16, 2024Updated 2 years ago
Are these results useful?