[USENIX Security 2025] SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
☆23Sep 18, 2025Updated last year
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:
- Code for Cascading and Proxy Membership Inference Attacks. NDSS 2026.☆11Aug 17, 2025Updated last year
- [EMNLP 2025] Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis☆11Apr 5, 2026Updated 7 months ago
- This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Secur…☆11Aug 24, 2022Updated 4 years ago
- ☆20Feb 11, 2024Updated 2 years ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆22Oct 5, 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.
- [NDSS'23] BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense☆17May 7, 2024Updated 2 years ago
- [COLM 2025] Official implementation of μKE - edit LLM knowledge while preserving memory dependencies via Matryoshka-style objectives.☆15Aug 20, 2025Updated last year
- Siren: Byzantine-robust Federated Learning via Proactive Alarming (SoCC '21)☆11Mar 28, 2024Updated 2 years ago
- Official repo for FSE'24 paper "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"☆19Mar 10, 2025Updated last year
- ☆18Aug 15, 2022Updated 4 years ago
- Machine Learning & Security Seminar @Purdue University☆26May 9, 2023Updated 3 years ago
- Official repo for "ProSec: Fortifying Code LLMs with Proactive Security Alignment"☆19Feb 26, 2026Updated 8 months ago
- [USENIX Security 2026] Membership Inference Attacks on Tokenizers of Large Language Models☆23May 22, 2026Updated 5 months ago
- Official Implementation of NeurIPS 2024 paper - BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens☆29Feb 17, 2026Updated 8 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- 🥇 Amazon Nova AI Challenge Winner - ASTRA emerged victorious as the top attacking team in Amazon's global AI safety competition, defeati…☆78May 11, 2026Updated 5 months ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆21Jan 27, 2024Updated 2 years ago
- ☆51Sep 4, 2026Updated 2 months ago
- ☆17Sep 4, 2024Updated 2 years ago
- [CVPR'24] LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning☆15Apr 17, 2026Updated 6 months ago
- [ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening☆10Dec 18, 2025Updated 10 months ago
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆30Dec 31, 2024Updated 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☆60Jun 2, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A toolbox for backdoor attacks.☆22Jan 13, 2023Updated 3 years ago
- ☆12May 27, 2022Updated 4 years ago
- [NDSS 2025] CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling☆20Jan 18, 2025Updated last year
- Official repository for CVPR'23 paper: Detecting Backdoors in Pre-trained Encoders☆39Sep 25, 2023Updated 3 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Apr 5, 2022Updated 4 years ago
- Source code of NAACL 2025 Findings "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models"☆16Dec 16, 2025Updated 10 months ago
- Code for NDSS 2022 paper "MIRROR: Model Inversion for Deep Learning Network with High Fidelity"☆28May 9, 2023Updated 3 years ago
- [ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning☆61Dec 11, 2024Updated last year
- [ACL2025 main] Official implementation of "LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjo…☆20Mar 16, 2026Updated 7 months 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.
- [CVPR'25] CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI☆55Oct 25, 2026Updated last week
- ☆19Jul 18, 2024Updated 2 years ago
- ☆16Apr 4, 2024Updated 2 years ago
- ☆26Dec 1, 2022Updated 3 years ago
- Official code for the paper "Context-aware Membership Inference Attacks against Pre-trained Models", accepted at EMNLP 2025☆13Sep 26, 2025Updated last year
- [ICML'24] Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss☆10Jun 3, 2024Updated 2 years ago
- [NeurIPS 2024] "Membership Inference on Text-to-image Diffusion Models via Conditional Likelihood Discrepancy"☆12Sep 15, 2025Updated last year