A new algorithm that formulates jailbreaking as a reasoning problem.
☆26Jul 2, 2025Updated last year
Alternatives and similar repositories for Adversarial-Reasoning
Users that are interested in Adversarial-Reasoning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆37Jul 2, 2026Updated 2 months ago
- ☆53Feb 25, 2026Updated 6 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆70Jun 9, 2025Updated last year
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆84Updated this week
- ☆68May 21, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Fine-tuning base models to build robust task-specific models☆36Apr 11, 2024Updated 2 years ago
- Official code implementation of SKU, Accepted by ACL 2024 Findings☆20Dec 18, 2024Updated last year
- Corresponding code to "FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems" @ CVPR 2021☆13Jun 22, 2021Updated 5 years ago
- TAP: An automated jailbreaking method for black-box LLMs☆247Dec 10, 2024Updated last year
- ☆18Jul 3, 2025Updated last year
- Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models☆36Oct 6, 2025Updated 11 months ago
- ☆42Aug 11, 2026Updated last month
- ICCV 2023 - AdaptGuard: Defending Against Universal Attacks for Model Adaptation☆11Dec 23, 2023Updated 2 years ago
- ☆12Apr 25, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆11Jul 3, 2024Updated 2 years ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆17Apr 24, 2024Updated 2 years ago
- ☆14Oct 17, 2024Updated last year
- ☆15Jul 24, 2022Updated 4 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆40Oct 3, 2023Updated 2 years ago
- Generate custom text files for dataloader within UDA methods☆14May 24, 2023Updated 3 years ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks☆14Feb 6, 2024Updated 2 years ago
- ☆12May 6, 2022Updated 4 years ago
- ☆15Jun 6, 2023Updated 3 years 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.
- Prompt Generator model for Stable Diffusion Models☆12Jun 20, 2023Updated 3 years ago
- To Trust Or Not To Trust Your Vision-Language Model's Prediction☆15May 30, 2025Updated last year
- ☆40May 17, 2025Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆40Jan 17, 2025Updated last year
- ☆15Dec 10, 2024Updated last year
- ☆205Nov 26, 2023Updated 2 years ago
- ☆13Oct 14, 2020Updated 5 years ago
- A very limited implementation of arXiv:1904.00759☆13Dec 2, 2019Updated 6 years ago
- Code and data repository for "The Mirage of Model Editing: Revisiting Evaluation in the Wild"☆18Aug 27, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ECCV 2022☆16Aug 3, 2022Updated 4 years ago
- [ACL'26] Official Repository for The Paper: What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time☆21Apr 7, 2026Updated 5 months ago
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆21Apr 15, 2024Updated 2 years ago
- A controllable and interactive simulation framework for vision research.☆16May 25, 2026Updated 3 months ago
- [ICLR 2025] Official implementation for "StringLLM: Understanding the String Processing Capability of Large Language Models"☆22Jan 23, 2025Updated last year
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆12Jun 18, 2024Updated 2 years ago
- Evaluating Durability: Benchmark Insights into Multimodal Watermarking☆12Jun 7, 2024Updated 2 years ago