skywalker023 / confaide
π€« Code and benchmark for our ICLR 2024 spotlight paper: "Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory"
β40Updated last year
Alternatives and similar repositories for confaide:
Users that are interested in confaide are comparing it to the libraries listed below
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Modelsβ80Updated 6 months ago
- β41Updated last month
- β37Updated last year
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Modelsβ17Updated 7 months ago
- Official code implementation of SKU, Accepted by ACL 2024 Findingsβ13Updated 2 months ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022β29Updated 2 years ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"β54Updated 5 months ago
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156β30Updated last year
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888β35Updated 9 months ago
- Official Repository for Dataset Inference for LLMsβ32Updated 7 months ago
- β25Updated 5 months ago
- Restore safety in fine-tuned language models through task arithmeticβ27Updated 11 months ago
- β11Updated 2 years ago
- β20Updated 7 months ago
- β15Updated last year
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024β69Updated 5 months ago
- β49Updated 7 months ago
- About Official PyTorch implementation of "Query-Efficient Black-Box Red Teaming via Bayesian Optimization" (ACL'23)β14Updated last year
- β30Updated 5 months ago
- β53Updated 2 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.β69Updated this week
- β23Updated 10 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)β46Updated last week
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMsβ35Updated last month
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineerβ38Updated 9 months ago
- β21Updated last year
- β33Updated last year
- RΓΆttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"β85Updated 2 weeks ago
- β25Updated last year
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.β85Updated 9 months ago