kangjie-chen / BadPre
☆10Updated 2 years ago
Related projects: ⓘ
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆37Updated 2 years ago
- Repository for Towards Codable Watermarking for Large Language Models☆26Updated last year
- Anti-Backdoor learning (NeurIPS 2021)☆76Updated last year
- Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"☆15Updated 3 years ago
- A toolbox for backdoor attacks.☆19Updated last year
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆21Updated 2 years ago
- ☆12Updated 5 months ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆52Updated last year
- ☆17Updated 6 months ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆16Updated last year
- ☆24Updated last year
- ☆23Updated last year
- ☆73Updated 3 years ago
- TrojanLM: Trojaning Language Models for Fun and Profit☆15Updated 3 years ago
- ☆17Updated 2 years ago
- Hidden backdoor attack on NLP systems☆45Updated 2 years ago
- ☆13Updated 2 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆23Updated 2 years ago
- Official implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.☆26Updated 2 years ago
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆47Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆49Updated last year
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆29Updated 6 months ago
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 3 months ago
- Code release for DeepJudge (S&P'22)☆50Updated last year
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆47Updated 4 years ago
- ☆27Updated 2 years ago
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆111Updated last month
- 复现了下Neural Cleanse这篇论文,真的是简单而有效,发在了okaland☆29Updated 3 years ago
- Exploring the Orthogonality and Linearity of Backdoor Attacks [IEEE S&P 2024]☆16Updated last month
- ☆12Updated 9 months ago