Internal Consistency Regularization (CROW) for LLM Backdoor Elimination - Paper accepted to ICML 2025
☆18May 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 8 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 5 years ago
- NJUQE is an open-source toolkit to build machine translation quality estimation models.☆12Sep 10, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆16Feb 26, 2025Updated last year
- JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning☆11Nov 3, 2024Updated 2 years ago
- The implementation for our paper, "Improving Simultaneous Machine Translation with Monolingual Data," accepted to AAAI 2023. 🎉☆12Jul 19, 2023Updated 3 years ago
- Disguising Attacks with Explanation-Aware Backdoors (IEEE S&P 2023)☆13Jan 3, 2026Updated 10 months ago
- ☆26May 27, 2020Updated 6 years ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆25May 20, 2025Updated last year
- [Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks☆13Feb 26, 2023Updated 3 years ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 5 months ago
- Code and dataset for the paper: "Can Editing LLMs Inject Harm?" [AAAI'26]☆21Dec 26, 2025Updated 10 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆23Oct 25, 2024Updated 2 years ago
- Official implementation of the USENIX Security 2024 paper ModelGuard: Information-Theoretic Defense Against Model Extraction Attacks.☆25Dec 6, 2023Updated 2 years ago
- Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning (ICLR 2021)☆24Mar 18, 2021Updated 5 years ago
- [COLM'24] How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?☆23Oct 13, 2024Updated 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
- Can Knowledge Editing Really Correct Hallucinations? (ICLR 2025)☆28Aug 10, 2025Updated last year
- [BMVC 2023] Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning☆18Sep 1, 2023Updated 3 years ago
- A method that can convert TFLite models to PyTorch Model (ICSE'24)☆12Jan 19, 2024Updated 2 years ago
- ☆28Feb 1, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆43May 21, 2025Updated last year
- This repository contains the code and experiments related to our paper: "Mitigating Unintended Memorization with LoRA in Federated Learni…☆14Apr 1, 2025Updated last year
- [NeurIPS 2025] Reasoning Models Better Express Their Confidence"☆23Nov 19, 2025Updated last year
- Robust Federated Learning for Large Language Models in Adversarial Wireless Environments☆16Mar 7, 2025Updated last year
- With the rapid adoption of smartphones, tablets, and mobile apps, they are increasingly becoming part of children’s daily life for amusem…☆12Apr 7, 2017Updated 9 years ago
- Official implementation for paper "FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning" (NeurIPS 2023).☆13Oct 25, 2024Updated 2 years ago
- ☆14Apr 23, 2026Updated 6 months ago
- [ICLR 2026] Data and Code for Paper Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models☆14Feb 2, 2026Updated 9 months ago
- Code for the paper: Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions☆12Mar 13, 2024Updated 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.
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆32Nov 2, 2025Updated last year
- Official code for "DCT-CryptoNets: Scaling Private Inference in the Frequency Domain" [ICLR 2025]☆10Feb 25, 2025Updated last year
- Implementation of "DeepWriter: A Multi-Stream Deep CNN for Text-independent Writer Identification"☆16Feb 3, 2020Updated 6 years ago
- [NeurIPS'25] VLMs Can Aggregate Scattered Training Patches☆14Jun 5, 2025Updated last year
- Pytorch implementation of NPAttack☆13Jul 7, 2020Updated 6 years ago
- Repository for Knowledge Enhanced Machine Learning Pipeline (KEMLP)☆10Jun 5, 2021Updated 5 years ago
- Implementation of our paper in EMNLP 2022, focused on the relationship between parent and child in transfer learning for low-resourc…☆17Dec 7, 2022Updated 3 years ago
Are these results useful?