Composite Backdoor Attacks Against Large Language Models
☆23Apr 12, 2024Updated last year
Alternatives and similar repositories for CBA
Users that are interested in CBA are comparing it to the libraries listed below
Sorting:
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆32Jul 11, 2022Updated 3 years ago
- ☆26Aug 21, 2024Updated last year
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆20Aug 10, 2024Updated last year
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆22Jul 3, 2024Updated last year
- Machine Learning & Security Seminar @Purdue University☆25May 9, 2023Updated 2 years ago
- ☆19Nov 6, 2023Updated 2 years ago
- ☆23Aug 24, 2020Updated 5 years ago
- This is the repository for USENIX Security 2023 paper "Hard-label Black-box Universal Adversarial Patch Attack".☆15Sep 5, 2023Updated 2 years ago
- A toolbox for backdoor attacks.☆23Jan 13, 2023Updated 3 years ago
- ☆28Aug 21, 2023Updated 2 years ago
- [SIGIR'25] Code of "Generative Recommender with End-to-End Learnable Item Tokenization".☆24Apr 17, 2025Updated 11 months ago
- ☆27Nov 9, 2022Updated 3 years ago
- ☆26Dec 1, 2022Updated 3 years ago
- Official Implementation for "Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approxim…☆12Aug 14, 2024Updated last year
- Gaussian Membership Inference Privacy (NeurIPS 2023)☆12Jul 27, 2024Updated last year
- [IEEE TIP] Offical implementation for the work "BadCM: Invisible Backdoor Attack against Cross-Modal Learning".☆14Aug 30, 2024Updated last year
- ☆11May 16, 2025Updated 10 months ago
- Code Repository for the Paper ---Revisiting the Assumption of Latent Separability for Backdoor Defenses (ICLR 2023)☆47Feb 28, 2023Updated 3 years ago
- Watermarking LLM papers up-to-date☆11Dec 17, 2023Updated 2 years ago
- some baseline attack method by pytorch☆11Oct 13, 2021Updated 4 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Sep 11, 2022Updated 3 years ago
- ☆16Mar 31, 2025Updated 11 months ago
- Distilling Task-Specific Knowledge from BERT into Simple Neural Networks.☆15Aug 28, 2020Updated 5 years ago
- Contains implementation of denoising algorithms.☆11Jul 16, 2020Updated 5 years ago
- ☆16Jul 23, 2022Updated 3 years ago
- The Latex template for Southeast University. 东南大学学位论文latex模板☆21Dec 4, 2023Updated 2 years ago
- ☆21Jan 15, 2026Updated 2 months ago
- This is the repository for the AI2019, tutorial on adversarial machine learning☆17Jul 20, 2020Updated 5 years 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 3 years ago
- Keys for Programming Assignments of Coursera Course Deep Learning Specialization by Andrew Ng☆20Jan 12, 2019Updated 7 years ago
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆42Feb 11, 2026Updated last month
- ☆13Dec 28, 2023Updated 2 years ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆65Apr 24, 2024Updated last year
- Identifying the compiler family, version and compiler flags that generated a binary☆19Dec 19, 2019Updated 6 years ago
- ☆14Dec 12, 2023Updated 2 years ago
- Javascript SDK for CopyFactory trade copying API. Can copy trades both between MetaTrader 5 (MT5) and MetaTrader 4 (MT4)☆17Nov 8, 2023Updated 2 years ago
- The official PyTorch code for AAAI'23 Paper "Sparse Coding in a Dual Memory System for Lifelong Learning"☆12Feb 15, 2023Updated 3 years ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆67Nov 14, 2025Updated 4 months ago
- 复现论文《Distilling Task-Specific Knowledge from BERT into Simple Neural Networks》☆16Jun 13, 2021Updated 4 years ago