Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
☆67Apr 24, 2024Updated 2 years ago
Alternatives and similar repositories for rlhf-poisoning
Users that are interested in rlhf-poisoning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆119Jun 13, 2024Updated 2 years ago
- ☆60May 30, 2024Updated 2 years ago
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆20Oct 22, 2024Updated last year
- ☆33Jun 24, 2024Updated 2 years ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆57Aug 17, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- This is an official code repository for CVPR 2025 paper BadVision.☆16Nov 18, 2025Updated 9 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆357Feb 23, 2024Updated 2 years ago
- ☆42May 21, 2025Updated last year
- Automatic Jailbreaking of the Text-to-Image Generative AI Systems☆15Jun 23, 2024Updated 2 years ago
- ☆134Jul 29, 2026Updated 2 weeks ago
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆17Apr 3, 2026Updated 4 months ago
- offical implementation of Jailbreak-R1☆15Jul 16, 2025Updated last year
- Implementation of our ICLR 2021 paper: Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples.☆11Mar 9, 2021Updated 5 years ago
- Backdoor Cleansing with Unlabeled Data (CVPR 2023)☆12Apr 6, 2023Updated 3 years ago
- 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.
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆86Oct 23, 2024Updated last year
- Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages." Paper accepted at Findings of EMNLP 2024☆18Mar 25, 2025Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆66Jan 11, 2025Updated last year
- ☆10Jul 28, 2022Updated 4 years ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆118Sep 27, 2024Updated last year
- ☆24Jan 17, 2025Updated last year
- ☆34Aug 11, 2022Updated 4 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆36Jan 9, 2023Updated 3 years ago
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆30Sep 18, 2025Updated 11 months ago
- 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.
- Privacy backdoors☆50Apr 28, 2024Updated 2 years ago
- Example TrojAI Submission☆27Dec 6, 2024Updated last year
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]☆36Jul 3, 2021Updated 5 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆65May 8, 2023Updated 3 years ago
- ☆38Oct 17, 2024Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆33Jan 23, 2025Updated last year
- ☆14Mar 23, 2023Updated 3 years ago
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆34Nov 8, 2024Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆346May 13, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆90Mar 15, 2024Updated 2 years ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆392Jan 23, 2025Updated last year
- Implementation of the paper "Improving the Accuracy-Robustness Trade-off of Classifiers via Adaptive Smoothing".☆10Feb 6, 2024Updated 2 years ago
- Official implementation for "RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards"☆17Jan 31, 2026Updated 6 months ago
- ☆22Sep 16, 2022Updated 3 years ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated 10 months ago
- ☆24Jul 25, 2024Updated 2 years ago