schroederdewitt / perfectly-secure-steganography
Contains open source code for the paper "Perfectly-secure Steganography using Minimum Entropy Coupling"
☆53Updated last year
Alternatives and similar repositories for perfectly-secure-steganography:
Users that are interested in perfectly-secure-steganography are comparing it to the libraries listed below
- Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.☆111Updated 10 months ago
- Code to break Llama Guard☆31Updated last year
- Code for our S&P'21 paper: Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding☆51Updated 2 years ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆107Updated 2 years ago
- Starter kit and data loading code for the Trojan Detection Challenge NeurIPS 2022 competition☆33Updated last year
- ☆123Updated 3 years ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆68Updated last year
- ☆294Updated last year
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆86Updated 11 months ago
- ☆34Updated last year
- ☆29Updated 10 months ago
- Privacy backdoors☆51Updated 11 months ago
- ☆27Updated last month
- ☆54Updated 2 years ago
- ☆47Updated 3 years ago
- ☆49Updated 4 years ago
- Fluent student-teacher redteaming☆20Updated 9 months ago
- ☆24Updated 3 years ago
- ☆35Updated 6 months ago
- Pytorch Datasets for Easy-To-Hard☆27Updated 3 months ago
- Demo code for the paper: One Thing to Fool them All: Generating Interpretable, Universal, and Physically-Realizable Adversarial Features☆12Updated last year
- ☆58Updated last year
- A curated list of academic events on AI Security & Privacy☆148Updated 8 months ago
- ☆97Updated last year
- ☆55Updated 2 months ago
- Certified robustness "for free" using off-the-shelf diffusion models and classifiers☆40Updated last year
- Official Implementation of the paper "Three Bricks to Consolidate Watermarks for LLMs"☆46Updated last year
- ☆26Updated 3 years ago
- ☆54Updated 10 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆111Updated last year