ethz-spylab / rlhf-poisoningView external linksLinks
Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
☆66Apr 24, 2024Updated last year
Alternatives and similar repositories for rlhf-poisoning
Users that are interested in rlhf-poisoning are comparing it to the libraries listed below
Sorting:
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆116Jun 13, 2024Updated last year
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆57Aug 17, 2024Updated last year
- ☆23Jan 17, 2025Updated last year
- Backdoor Cleansing with Unlabeled Data (CVPR 2023)☆12Apr 6, 2023Updated 2 years ago
- ☆10Jul 28, 2022Updated 3 years ago
- ☆58May 30, 2024Updated last year
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆19Oct 22, 2024Updated last year
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆33Nov 8, 2024Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆65Jan 11, 2025Updated last year
- A fast + lightweight implementation of the GCG algorithm in PyTorch☆317May 13, 2025Updated 9 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆220Dec 10, 2024Updated last year
- 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…☆338Feb 23, 2024Updated last year
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆21Jul 3, 2024Updated last year
- TACL 2025: Investigating Adversarial Trigger Transfer in Large Language Models☆19Aug 17, 2025Updated 6 months ago
- ☆34Aug 11, 2022Updated 3 years ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆84Oct 23, 2024Updated last year
- ☆33Jun 24, 2024Updated last year
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated 4 months ago
- ☆121Feb 3, 2025Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆88Mar 15, 2024Updated last year
- ☆22Sep 16, 2022Updated 3 years ago
- ☆24Jul 25, 2024Updated last year
- ☆51Oct 23, 2023Updated 2 years ago
- Example TrojAI Submission☆27Dec 6, 2024Updated last year
- ☆24Jun 17, 2025Updated 8 months ago
- A toolbox for backdoor attacks.☆23Jan 13, 2023Updated 3 years ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆23Jul 26, 2024Updated last year
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆70Feb 5, 2024Updated 2 years ago
- Debiasing Through Data Attribution☆12May 23, 2024Updated last year
- On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them [NeurIPS 2020]☆36Jul 3, 2021Updated 4 years ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90May 19, 2024Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆109Sep 27, 2024Updated last year
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆63May 8, 2023Updated 2 years ago
- ☆30Jun 19, 2023Updated 2 years ago
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆27Sep 18, 2025Updated 4 months ago
- Official Repository for Dataset Inference for LLMs☆43Jul 25, 2024Updated last year
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆227Dec 22, 2024Updated last year
- Implementation of our ICLR 2021 paper: Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples.☆11Mar 9, 2021Updated 4 years ago
- ACL24☆11Jun 7, 2024Updated last year