parameterlab / mia-scalingLinks
Source code of NAACL 2025 Findings "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models"
☆10Updated 4 months ago
Alternatives and similar repositories for mia-scaling
Users that are interested in mia-scaling are comparing it to the libraries listed below
Sorting:
- Official Repository for Dataset Inference for LLMs☆34Updated 11 months ago
- Benchmarking MIAs against LLMs.☆19Updated 8 months ago
- Code for the WWW'23 paper "Sanitizing Sentence Embeddings (and Labels) for Local Differential Privacy"☆12Updated 2 years ago
- Official repo for the paper: Recovering Private Text in Federated Learning of Language Models (in NeurIPS 2022)☆56Updated 2 years ago
- LAMP: Extracting Text from Gradients with Language Model Priors (NeurIPS '22)☆24Updated last month
- ☆13Updated 2 years ago
- ☆20Updated last year
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆24Updated 3 years ago
- ☆73Updated 3 years ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90Updated last year
- ☆44Updated 4 months ago
- ☆29Updated last year
- Revisiting Character-level Adversarial Attacks for Language Models, ICML 2024☆16Updated 4 months ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 11 months ago
- Private Adaptive Optimization with Side Information (ICML '22)☆16Updated 3 years ago
- TrojanLM: Trojaning Language Models for Fun and Profit☆16Updated 4 years ago
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆24Updated 3 years ago
- The code and data for "Are Large Pre-Trained Language Models Leaking Your Personal Information?" (Findings of EMNLP '22)☆24Updated 2 years ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆29Updated 2 years ago
- ☆43Updated 2 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Updated 2 years ago
- ☆24Updated 2 years ago
- ☆66Updated 4 years ago
- A Synthetic Dataset for Personal Attribute Inference (NeurIPS'24 D&B)☆43Updated 6 months ago
- ☆6Updated 2 years ago
- ☆39Updated 10 months ago
- ☆28Updated 8 months ago
- ☆26Updated last year
- [ECCV24] "Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning" by Chongyu Fan*, Jiancheng Liu*, Alfred Hero, …☆21Updated last month
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆55Updated last year