Internal Consistency Regularization (CROW) for LLM Backdoor Elimination - Paper accepted to ICML 2025
☆16May 6, 2025Updated last year
Alternatives and similar repositories for CROW
Users that are interested in CROW 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 associated with ICML (2024). "Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normaliz…☆11Feb 22, 2026Updated 6 months ago
- [NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"☆26Aug 20, 2025Updated last year
- Official implementation repository for the paper Towards General Conceptual Model Editing via Adversarial Representation Engineering.☆20Dec 6, 2024Updated last year
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆25Oct 21, 2021Updated 4 years ago
- JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning☆10Nov 3, 2024Updated last year
- 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.
- ☆15Feb 26, 2025Updated last year
- The implementation for our paper, "Improving Simultaneous Machine Translation with Monolingual Data," accepted to AAAI 2023. 🎉☆12Jul 19, 2023Updated 3 years ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆25May 20, 2025Updated last year
- ☆23Oct 25, 2024Updated last year
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 2 months ago
- ACL 2023 paper "A Critical Evaluation of Evaluations for Long-form Question Answering"☆21Mar 22, 2024Updated 2 years ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?" [AAAI'26]☆21Dec 26, 2025Updated 8 months ago
- [COLM'24] How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?☆23Oct 13, 2024Updated last year
- Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)☆24Mar 18, 2021Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Official implementation of the USENIX Security 2024 paper ModelGuard: Information-Theoretic Defense Against Model Extraction Attacks.☆25Dec 6, 2023Updated 2 years ago
- Test implementation of "Aligned Cross Entropy for Non-Autoregressive Machine Translation" https://arxiv.org/abs/2004.01655☆21Jul 25, 2024Updated 2 years ago
- Code for the paper: Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions☆12Mar 13, 2024Updated 2 years ago
- Robust Federated Learning for Large Language Models in Adversarial Wireless Environments☆16Mar 7, 2025Updated last year
- Two-party Privacy-preserving Neural Network Training using Split Learning and Homomorphic Encryption (CKKS Scheme)☆13Sep 23, 2025Updated 11 months ago
- [NeurIPS'24] Official implement of "PrivCirNet: Efficient Private Inference via Block Circulant Transformation"☆14Feb 26, 2026Updated 6 months ago
- ☆14May 23, 2023Updated 3 years ago
- Official code for FAccT'21 paper "Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning" https://arxiv.org/abs…☆13Mar 9, 2021Updated 5 years ago
- [ICLR 2025] Official repository for the paper "Influence-Guided Diffusion for Dataset Distillation".☆15Feb 12, 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.
- ☆42May 21, 2025Updated last year
- [NeurIPS 2025] Reasoning Models Better Express Their Confidence"☆23Nov 19, 2025Updated 9 months ago
- ☆32Jun 13, 2026Updated 2 months ago
- Official implementation for paper "FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning" (NeurIPS 2023).☆13Oct 25, 2024Updated last year
- Code release for MPCViT accepted by ICCV 2023☆17Jan 6, 2025Updated last year
- Implementation for the protocols described in https://eprint.iacr.org/2023/1700☆14Apr 29, 2026Updated 4 months ago
- Pytorch implementation of NPAttack☆12Jul 7, 2020Updated 6 years ago
- [NDSS 2025] CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling☆19Jan 18, 2025Updated last year
- Repository for Knowledge Enhanced Machine Learning Pipeline (KEMLP)☆10Jun 5, 2021Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICSE-SEIP'21] Robustness of on-device Models: AdversarialAttack to Deep Learning Models on Android Apps☆15Jun 2, 2022Updated 4 years ago
- ☆20Feb 18, 2024Updated 2 years ago
- Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression☆14Mar 22, 2025Updated last year
- ☆20Oct 29, 2023Updated 2 years ago
- ☆17Feb 3, 2022Updated 4 years ago
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses☆27Updated this week
- ☆24Dec 8, 2024Updated last year