[NeurIPS '25] Code for Paper "IF-Guide: Influence Function-Guided Suppression of Harmful Training Data for Reducing LLM Toxicity"
☆14Oct 22, 2025Updated last year
Alternatives and similar repositories for IF-Guide
Users that are interested in IF-Guide are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The implementation of our IEEE S&P 2024 paper "Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples".☆11Jun 28, 2024Updated 2 years ago
- A simple Jax implementation of influence functions.☆21Apr 9, 2024Updated 2 years ago
- A simple and efficient baseline for data attribution☆11Nov 10, 2023Updated 2 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Feb 27, 2020Updated 6 years ago
- ☆14Feb 4, 2026Updated 8 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Tiny Tutorial on https://arxiv.org/abs/1703.04730☆14Nov 19, 2019Updated 6 years ago
- ☆12May 6, 2022Updated 4 years ago
- Official Implementation of Robustifying and Boosting Training-Free Neural Architecture Search☆12Mar 12, 2024Updated 2 years ago
- ☆51Mar 24, 2023Updated 3 years ago
- C++ API and application example for BITalino☆12Oct 19, 2016Updated 10 years ago
- Official Implementation for "Nearest Is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks" (CVPR 2…☆12Aug 14, 2024Updated 2 years ago
- KNN Defense Against Clean Label Poisoning Attacks☆13Sep 24, 2021Updated 5 years ago
- Code for the CVPR '23 paper, "Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning"☆10Jun 9, 2023Updated 3 years ago
- [ICLR 2024] "Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality" by Xuxi Chen*, Yu Yang*, Zhangyang Wang, Baha…☆15May 18, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆40Dec 27, 2022Updated 3 years ago
- [ICML 2026] REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations☆30Jul 6, 2026Updated 3 months ago
- ☆11May 1, 2025Updated last year
- Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks☆13Dec 18, 2023Updated 2 years ago
- Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data. NeurIPS'25 Spotlight☆12Jul 30, 2025Updated last year
- Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity☆16May 7, 2026Updated 5 months ago
- This repository contains the code for the paper "LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Sig…☆24Apr 15, 2026Updated 6 months ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 4 months ago
- Code for the paper "Do Unlearning Methods Remove Information from Language Model Weights?"☆13Oct 9, 2024Updated 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.
- A tool of translating virtual address of user space to physical address.☆22Jul 3, 2017Updated 9 years ago
- [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…☆15Nov 27, 2023Updated 2 years ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆16Jan 13, 2023Updated 3 years ago
- PyTorch implementation of our ICLR 2023 paper titled "Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?".☆12Mar 13, 2023Updated 3 years ago
- [EMNLP'24 oral] On Training Data Influence of GPT Models☆11Jun 6, 2025Updated last year
- Large-batch Training, Neural Network Optimization☆11Nov 8, 2019Updated 6 years ago
- [ICML25] Official repo for "Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond…☆25Sep 27, 2025Updated last year
- ☆20Oct 28, 2025Updated 11 months ago
- csl: PyTorch-based Constrained Learning☆11Jun 1, 2022Updated 4 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆16Feb 26, 2025Updated last year
- ☆17Jun 5, 2024Updated 2 years ago
- ☆14Oct 7, 2022Updated 4 years ago
- [NeurIPS 2025] SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations☆73Oct 14, 2026Updated last week
- [NeurIPS 2025] Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack☆15Nov 19, 2025Updated 11 months ago
- [CVPR 2024] "Data Poisoning based Backdoor Attacks to Contrastive Learning": official code implementation.☆16Feb 10, 2025Updated last year
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Jan 3, 2023Updated 3 years ago