[USENIX Security 2025] SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
☆23Sep 18, 2025Updated 11 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
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆22Oct 5, 2025Updated 10 months ago
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆17May 7, 2024Updated 2 years ago
- Siren: Byzantine-robust Federated Learning via Proactive Alarming (SoCC '21)☆11Mar 28, 2024Updated 2 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.
- ☆16Dec 29, 2023Updated 2 years ago
- Official repo for "ProSec: Fortifying Code LLMs with Proactive Security Alignment"☆18Feb 26, 2026Updated 5 months ago
- ☆18Aug 15, 2022Updated 4 years ago
- Official repo for FSE'24 paper "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"☆19Mar 10, 2025Updated last year
- [USENIX Security 2026] Membership Inference Attacks on Tokenizers of Large Language Models☆21May 22, 2026Updated 2 months ago
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens☆29Feb 17, 2026Updated 6 months ago
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning☆15Apr 17, 2026Updated 4 months ago
- ☆17Sep 4, 2024Updated last year
- ☆15Jun 28, 2025Updated last year
- 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.
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆30Dec 31, 2024Updated last year
- 🥇 Amazon Nova AI Challenge Winner - ASTRA emerged victorious as the top attacking team in Amazon's global AI safety competition, defeati…☆76May 11, 2026Updated 3 months ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- ☆50Aug 10, 2026Updated last week
- [ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening☆10Dec 18, 2025Updated 8 months ago
- [NDSS 2025] CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling☆19Jan 18, 2025Updated last year
- [Oakland 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆29Apr 15, 2025Updated last year
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆57Jun 2, 2025Updated last year
- A toolbox for backdoor attacks.☆22Jan 13, 2023Updated 3 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☆38Sep 25, 2023Updated 2 years ago
- Source code of NAACL 2025 Findings "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models"☆16Dec 16, 2025Updated 8 months ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆23Apr 5, 2022Updated 4 years ago
- [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
- [CVPR'25] CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI☆51May 4, 2026Updated 3 months ago
- ☆20Jul 18, 2024Updated 2 years ago
- ☆26Dec 1, 2022Updated 3 years ago
- ☆16Apr 4, 2024Updated 2 years ago
- Machine Learning & Security Seminar @Purdue University☆26May 9, 2023Updated 3 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.
- Code for NDSS 2022 paper "MIRROR: Model Inversion for Deep Learning Network with High Fidelity"☆28May 9, 2023Updated 3 years ago
- [NeurIPS 2024] "Membership Inference on Text-to-image Diffusion Models via Conditional Likelihood Discrepancy"☆12Sep 15, 2025Updated 11 months ago
- ☆12May 27, 2022Updated 4 years ago
- 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
- This is the repository for USENIX Security 2023 paper "Hard-label Black-box Universal Adversarial Patch Attack".☆15Sep 5, 2023Updated 2 years ago
- Shadow Attack, LiRA, Quantile Regression and RMIA implementations in PyTorch (Online version)☆14Nov 8, 2024Updated last year
- 🔮Reasoning for Safer Code Generation; 🥇Winner Solution of Amazon Nova AI Challenge 2025☆40Aug 24, 2025Updated 11 months ago