[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.
☆17Jul 25, 2026Updated last month
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 4 months ago
- A prototype for innovative BGP anomaly detection system --- BGPShield.☆18Apr 7, 2026Updated 4 months ago
- DARWIN is a self-evolving LLM jailbreak framework that grows a reusable strategy pool through external extraction, sandbox filtering, his…☆66Jun 5, 2026Updated 2 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…☆232Apr 8, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆40Nov 4, 2024Updated last year
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion (NeurIPS 2024 Spotlight)☆15Mar 31, 2025Updated last year
- Paper list of LLM fingerprinting, based on our paper titled "SoK: Large Language Model Copyright Auditing via Fingerprinting".☆32Aug 28, 2025Updated 11 months ago
- ☆16Jul 15, 2025Updated last year
- ☆228Aug 17, 2025Updated last year
- code space of paper "Safety Layers in Aligned Large Language Models: The Key to LLM Security" (ICLR 2025)☆25Apr 26, 2025Updated last year
- ☆49Feb 8, 2025Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆37Oct 15, 2023Updated 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.
- NeurIPS'24 - LLM Safety Landscape☆40Oct 21, 2025Updated 10 months ago
- Official implementation of "Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference" (NDSS 2026)☆19Feb 28, 2026Updated 5 months ago
- Host CIFAR-10.2 Data Set☆13Sep 22, 2021Updated 4 years ago
- Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs☆12Nov 7, 2024Updated last year
- [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
- TRACE, a framework for turn-aware credit assignment for multi-turn jailbreak optimization☆21Jun 22, 2026Updated 2 months ago
- Test for Graph Unlearning Benchmark☆21Jul 12, 2025Updated last year
- Official Implementation of implicit reference attack☆11Oct 16, 2024Updated 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☆19May 23, 2026Updated 3 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.
- ☆11Jan 21, 2021Updated 5 years ago
- [ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"☆11Feb 20, 2025Updated last year
- Let you in a meta world of The Palace Museum☆22Aug 30, 2025Updated 11 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆153Jul 19, 2024Updated 2 years ago
- 2023美赛 MCM C题☆19May 13, 2023Updated 3 years ago
- ☆12Oct 29, 2023Updated 2 years ago
- ☆13Nov 12, 2024Updated last year
- NDSS 2020☆14May 28, 2020Updated 6 years ago
- 百度AI安全对抗赛第一名团队示例代码，基于官方给出的PGD修改，主要内容为L2-PGD+EOT。☆11Mar 17, 2021Updated 5 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.
- [EMNLP 2024 Findings] Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information☆13Oct 1, 2024Updated last year
- Code for NDSS '25 paper "Passive Inference Attacks on Split Learning via Adversarial Regularization"☆13Sep 16, 2024Updated last year
- Official repository for ALT (ALignment with Textual feedback).☆10Jul 25, 2024Updated 2 years ago
- ☆61Jun 5, 2024Updated 2 years ago
- ☆10Dec 9, 2024Updated last year
- ☆12Sep 29, 2024Updated last year
- c++高性能内存池☆11May 10, 2021Updated 5 years ago