☆24Aug 18, 2023Updated 2 years ago
Alternatives and similar repositories for neighborhood-curvature-mia
Users that are interested in neighborhood-curvature-mia are comparing it to the libraries listed below
Sorting:
- ☆19Mar 6, 2023Updated 3 years ago
- ☆25Nov 14, 2022Updated 3 years ago
- Public implementation of the paper "On the Importance of Difficulty Calibration in Membership Inference Attacks".☆16Dec 1, 2021Updated 4 years ago
- https://icml.cc/virtual/2023/poster/24354☆10Aug 15, 2023Updated 2 years ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆37Jun 10, 2024Updated last year
- Code for the paper "Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction" …☆12Sep 6, 2023Updated 2 years ago
- ☆15Apr 4, 2024Updated last year
- Code for the WWW'23 paper "Sanitizing Sentence Embeddings (and Labels) for Local Differential Privacy"☆12Feb 20, 2023Updated 3 years ago
- 🤫 Code and benchmark for our ICLR 2024 spotlight paper: "Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Con…☆50Dec 20, 2023Updated 2 years ago
- ☆15Apr 7, 2023Updated 2 years ago
- [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
- [EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP☆13Aug 17, 2023Updated 2 years ago
- ☆16Jan 10, 2025Updated last year
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Feb 27, 2020Updated 6 years ago
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆96Sep 17, 2025Updated 5 months ago
- ☆13Oct 20, 2022Updated 3 years ago
- Private Adaptive Optimization with Side Information (ICML '22)☆16Jun 23, 2022Updated 3 years ago
- Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]☆21Apr 15, 2024Updated last year
- ☆22May 28, 2025Updated 9 months ago
- ☆15Feb 21, 2024Updated 2 years ago
- This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Aji…☆242Nov 3, 2023Updated 2 years ago
- ☆43May 23, 2023Updated 2 years ago
- Implementation of Patch-wise Adversarial Regularization from "Learning Robust Global Representations by Penalizing Local Predictive Power…☆18Oct 27, 2019Updated 6 years ago
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆87Sep 12, 2024Updated last year
- Kaggle Heritage Health Prize Challenge☆19Dec 5, 2023Updated 2 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆19Jun 7, 2023Updated 2 years ago
- ☆22Sep 17, 2024Updated last year
- [ICML2023] Revisiting Data-Free Knowledge Distillation with Poisoned Teachers☆23Jul 7, 2024Updated last year
- Not All Poisons are Created Equal: Robust Training against Data Poisoning (ICML 2022)☆22Aug 8, 2022Updated 3 years ago
- Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confid…☆23May 8, 2023Updated 2 years ago
- Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"☆21Oct 26, 2023Updated 2 years ago
- [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models☆19Feb 18, 2025Updated last year
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆21Oct 1, 2022Updated 3 years ago
- Differentially-private transformers using HuggingFace and Opacus☆147Aug 28, 2024Updated last year
- ☆27Feb 20, 2024Updated 2 years ago
- ☆26Nov 25, 2023Updated 2 years ago
- ☆21Sep 21, 2021Updated 4 years ago
- Source code for the TMLR paper "Black-Box Prompt Learning for Pre-trained Language Models"☆57Sep 7, 2023Updated 2 years ago
- ☆24Apr 20, 2024Updated last year