[USENIX Security 2025] SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
☆20Sep 18, 2025Updated 6 months ago
Alternatives and similar repositories for SOFT
Users that are interested in SOFT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Secur…☆11Aug 24, 2022Updated 3 years ago
- ☆20Feb 11, 2024Updated 2 years ago
- ☆15Dec 29, 2023Updated 2 years ago
- ☆18Aug 15, 2022Updated 3 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆17May 7, 2024Updated last year
- A toolbox for backdoor attacks.☆23Jan 13, 2023Updated 3 years ago
- ☆12May 27, 2022Updated 3 years ago
- Source code of NAACL 2025 Findings "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models"☆15Dec 16, 2025Updated 3 months ago
- [NeurIPS 2024] "Membership Inference on Text-to-image Diffusion Models via Conditional Likelihood Discrepancy"☆12Sep 15, 2025Updated 6 months ago
- Siren: Byzantine-robust Federated Learning via Proactive Alarming (SoCC '21)☆11Mar 28, 2024Updated 2 years ago
- ☆16Sep 4, 2024Updated last year
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning☆15Jan 15, 2025Updated last year
- This is the repository for USENIX Security 2023 paper "Hard-label Black-box Universal Adversarial Patch Attack".☆15Sep 5, 2023Updated 2 years ago
- 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.
- Official repository for CVPR'23 paper: Detecting Backdoors in Pre-trained Encoders☆36Sep 25, 2023Updated 2 years ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆15Jan 13, 2023Updated 3 years ago
- ☆18Jun 15, 2021Updated 4 years ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆21Oct 5, 2025Updated 5 months ago
- Official repo for FSE'24 paper "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"☆18Mar 10, 2025Updated last year
- [ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning☆60Dec 11, 2024Updated last year
- ☆21May 23, 2025Updated 10 months ago
- a deep learning based drug target interaction prediction model☆11Nov 5, 2022Updated 3 years ago
- ☆26Dec 1, 2022Updated 3 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.
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆53Jun 2, 2025Updated 9 months ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Apr 5, 2022Updated 3 years ago
- ☆14May 8, 2024Updated last year
- ☆20Oct 28, 2025Updated 5 months ago
- Code for NDSS 2022 paper "MIRROR: Model Inversion for Deep Learning Network with High Fidelity"☆27May 9, 2023Updated 2 years ago
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆29Dec 31, 2024Updated last year
- ☆11May 18, 2025Updated 10 months ago
- [Oakland 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆28Apr 15, 2025Updated 11 months ago
- ☆46Feb 16, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆29Nov 19, 2023Updated 2 years ago
- ☆37Oct 17, 2024Updated last year
- Function secret sharing (FSS) primitives including distributed point/comparison function (DPF/DCF)☆30Updated this week
- [MM'23] ProTegO: Protect Text Content against OCR Extraction Attack☆14Mar 12, 2024Updated 2 years ago
- [AAAI 2024] Data-Free Hard-Label Robustness Stealing Attack☆15Mar 29, 2024Updated 2 years ago
- [ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening☆10Dec 18, 2025Updated 3 months ago
- ☆29Mar 9, 2025Updated last year