Panda Guard is designed for researching jailbreak attacks, defenses, and evaluation algorithms for large language models (LLMs).
☆68Mar 23, 2026Updated 2 months ago
Alternatives and similar repositories for panda-guard
Users that are interested in panda-guard are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official GitHub repository for the paper "Adversarial Attacks on Robotic Vision Language Action Models"☆34May 28, 2025Updated last year
- Code Implementation of Adversarial Prompt Evaluation paper☆14Sep 18, 2025Updated 8 months ago
- ☆135Feb 3, 2025Updated last year
- The official repository for guided jailbreak benchmark☆29Jul 28, 2025Updated 10 months ago
- ☆66May 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.
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆61Apr 8, 2024Updated 2 years ago
- AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.☆241Apr 21, 2026Updated last month
- ☆20May 14, 2025Updated last year
- [CVPR2025] T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation☆33Jul 10, 2025Updated 10 months ago
- ☆10Oct 21, 2024Updated last year
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Jul 9, 2024Updated last year
- ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models☆26Sep 27, 2025Updated 8 months ago
- Official Code Implementation for the CCS 2022 Paper "On the Privacy Risks of Cell-Based NAS Architectures"☆11Nov 21, 2022Updated 3 years ago
- KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality☆45May 19, 2026Updated last week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆60Oct 1, 2025Updated 7 months ago
- Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing☆14Feb 18, 2021Updated 5 years ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆192Apr 1, 2025Updated last year
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Aug 25, 2024Updated last year
- ☆22Jul 26, 2025Updated 10 months ago
- ☆10Jun 5, 2021Updated 4 years ago
- The official code of the paper: Semantic-guided Multi-mask Image Harmonization (ECCV2022)☆15Jul 20, 2022Updated 3 years ago
- Optimizing Review Generation Through Prompt Generation☆16Apr 15, 2024Updated 2 years ago
- Open-sourced evaluation suite from the Monitoring Monitorability paper☆76Apr 22, 2026Updated last month
- 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.
- ☆24May 23, 2025Updated last year
- SECURE: Benchmarking Generative Large Language Models as a Cyber Advisory☆17Aug 28, 2024Updated last year
- [NeurIPS 2023] and [ICLR 2024] for robustness certification.☆10Nov 30, 2024Updated last year
- ☆12Jun 13, 2025Updated 11 months ago
- ☆20Apr 23, 2024Updated 2 years ago
- [ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".☆172May 2, 2025Updated last year
- PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion☆371Updated this week
- ☆36Apr 13, 2026Updated last month
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆35Oct 19, 2023Updated 2 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.
- Casande-RL☆11May 9, 2023Updated 3 years ago
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…☆113Oct 11, 2024Updated last year
- Code for the paper "Multi-scale Diffusion Denoised Smoothing" (NeurIPS 2023)☆15Apr 30, 2024Updated 2 years ago
- [WSDM 2026] LookAhead Tuning: Safer Language Models via Partial Answer Previews☆17Dec 14, 2025Updated 5 months ago
- ☆34Nov 12, 2024Updated last year
- Official code implement of "Your Diffusion Model is Secretly a Certifiably Robust Classifier"☆18Feb 2, 2024Updated 2 years ago
- Code for the paper "SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness" (NeurIPS 2021)☆21Sep 27, 2022Updated 3 years ago