alps-lab / trojan-lm
TrojanLM: Trojaning Language Models for Fun and Profit
☆15Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for trojan-lm
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆21Updated 2 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆37Updated 2 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆78Updated last year
- ☆23Updated last year
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆55Updated last year
- ☆62Updated 4 years ago
- ☆18Updated 8 months ago
- Code for "Label-Consistent Backdoor Attacks"☆49Updated 4 years ago
- ☆25Updated 5 months ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆99Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- ☆13Updated 2 years ago
- Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"☆16Updated 3 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 2 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆17Updated last year
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆24Updated this week
- A curated list of trustworthy Generative AI papers. Daily updating...☆67Updated 2 months ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆41Updated 2 years ago
- Hidden backdoor attack on NLP systems☆46Updated 3 years ago
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆11Updated last year
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 2 years ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆50Updated 2 years ago
- ☆19Updated 2 months ago
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆22Updated 3 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆28Updated 11 months ago
- ☆26Updated 2 years ago
- ☆76Updated 3 years ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆18Updated last year
- A toolbox for backdoor attacks.☆19Updated last year
- ☆23Updated 2 years ago