[ICLR 2025] REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
☆13Feb 13, 2025Updated last year
Alternatives and similar repositories for REFINE
Users that are interested in REFINE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025] Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack☆15Nov 19, 2025Updated 10 months ago
- Paper list of LLM fingerprinting, based on our paper titled "SoK: Large Language Model Copyright Auditing via Fingerprinting".☆33Aug 28, 2025Updated last year
- Official implementation of "Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference" (NDSS 2026)☆22Feb 28, 2026Updated 6 months ago
- [IEEE TDSC] Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks☆16Oct 7, 2025Updated 11 months ago
- [NDSS 2025] Official code for our paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Wate…☆45Nov 5, 2024Updated last year
- 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.
- ☆227Aug 17, 2025Updated last year
- Official code for our paper "SoK: Large Language Model Copyright Auditing via Fingerprinting"☆20Dec 31, 2025Updated 8 months ago
- ☆18Feb 25, 2024Updated 2 years ago
- CCS 2025 | Neural-symbolic model adaptation integrating malware behavior-based domain concepts in paper "Combating Concept Drift with Exp…☆23May 11, 2026Updated 4 months ago
- Official implementation of the paper "From Optimization to Generalization: Fair Federated Learning against Quality Shift via Inter-Client…☆11Mar 13, 2025Updated last year
- ☆16Feb 26, 2025Updated last year
- Source code and scripts for the paper "Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks"☆20Dec 10, 2024Updated last year
- [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
- ☆18Jun 15, 2021Updated 5 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.
- Pytorch implementation of NPAttack☆13Jul 7, 2020Updated 6 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Apr 5, 2022Updated 4 years ago
- ☆27Jun 5, 2024Updated 2 years ago
- Implementation of ECCV 2020 "Sparse Adversarial Attack via Perturbation Factorization"☆27Aug 18, 2020Updated 6 years ago
- [TDSC 2024] Official code for our paper "FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model"☆23May 14, 2025Updated last year
- [ArXiv 2025] Imperceptible Jailbreaking against Large Language Models☆25Oct 7, 2025Updated 11 months ago
- ☆29Nov 9, 2022Updated 3 years ago
- a distributed read-only cache, based groupcache, using etcd as a registry, supports efficient concurrent reading.☆14Sep 25, 2023Updated 2 years ago
- ☆26Dec 1, 2022Updated 3 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.
- Official implementation of Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models☆16Mar 21, 2026Updated 5 months ago
- Source code of "TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification", ACL2024 (findings)☆15Nov 20, 2024Updated last year
- ESEC/FSE'21: Prediction-Preserving Program Simplification☆10Oct 4, 2022Updated 3 years ago
- Official Implementation for "Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models" (IE…☆30Mar 24, 2025Updated last year
- Adversarial Attack for Pre-trained Code Models☆10Jul 19, 2022Updated 4 years ago
- code for paper "Detecting Adversarial Data via Perturbation Forgery"☆18Jul 10, 2025Updated last year
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆48Feb 28, 2023Updated 3 years ago
- ☆24Nov 11, 2022Updated 3 years ago
- Implementation of An Invisible Black-box Backdoor Attack through Frequency Domain☆21Sep 29, 2022Updated 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.
- This technique modifies image data so that any model trained on it will bear an identifiable mark.☆46Aug 13, 2021Updated 5 years ago
- ☆19Sep 10, 2023Updated 3 years ago
- 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
- ☆21May 24, 2025Updated last year
- Explanation Optimization☆13Oct 16, 2020Updated 5 years ago
- ☆33Mar 4, 2022Updated 4 years ago
- Code for ICML 2023 paper "Reprogramming Pretrained Language Models for Antibody Sequence Infilling"☆25Sep 18, 2025Updated last year