haowang-cqu / graduation-project
本科毕业设计: 自然语言处理后门技术研究与实现
☆8Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for graduation-project
- ☆14Updated last year
- Official code for the ICCV2023 paper ``One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training''☆14Updated last year
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆14Updated last year
- This is the implementation of our paper 'Open-sourced Dataset Protection via Backdoor Watermarking', accepted by the NeurIPS Workshop on …☆19Updated 3 years ago
- [CVPR 2024] Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers☆15Updated 3 weeks ago
- This is the official implementation of our paper 'Black-box Dataset Ownership Verification via Backdoor Watermarking'.☆23Updated last year
- Defending against Model Stealing via Verifying Embedded External Features☆32Updated 2 years ago
- Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).☆31Updated last year
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆44Updated 7 months ago
- Data-Efficient Backdoor Attacks☆18Updated 2 years ago
- ☆19Updated 2 years ago
- ☆10Updated 5 months ago
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆26Updated 4 years ago
- The code for ECCV2022 (Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal)☆38Updated 2 years ago
- ☆9Updated 2 years ago
- Official code for "TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization", CVPR 2023☆13Updated last year
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆12Updated 3 months ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆29Updated last year
- ☆28Updated 2 years ago
- SEAT☆19Updated last year
- ☆17Updated last year
- official implementation of Towards Robust Model Watermark via Reducing Parametric Vulnerability☆12Updated 5 months ago
- ☆19Updated 3 years ago
- Codes for the ICLR 2022 paper: Trigger Hunting with a Topological Prior for Trojan Detection☆10Updated last year
- Code for Boosting fast adversarial training with learnable adversarial initialization (TIP2022)☆28Updated last year
- Marich is a model-agnostic extraction algorithm. It uses a public data to query a private model, aggregates the predicted labels, and con…☆7Updated last year
- ☆9Updated last year
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆23Updated last year
- ☆10Updated 2 years ago
- ICCV 2021 papers and code focus on adversarial attacks and defense☆11Updated 3 years ago