lijiachun123 / TrojAi
competition
☆17Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for TrojAi
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆27Updated 3 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 2 years ago
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆47Updated 2 years ago
- ☆12Updated 3 years ago
- ☆19Updated 2 years ago
- ☆16Updated 3 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- Code for identifying natural backdoors in existing image datasets.☆15Updated 2 years ago
- ☆62Updated 4 years ago
- ☆19Updated 4 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
- 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
- Code release for DeepJudge (S&P'22)☆51Updated last year
- ☆23Updated last year
- AdvDoor: Adversarial Backdoor Attack of Deep Learning System☆30Updated 2 weeks ago
- ☆23Updated last year
- [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆18Updated last month
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 5 months ago
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆15Updated last year
- ☆43Updated 2 months ago
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆49Updated last week
- ☆19Updated 2 months ago
- ☆17Updated 3 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆55Updated last year
- Official implementation of (CVPR 2022 Oral) Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks.☆26Updated 2 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆78Updated last year
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆50Updated 2 years ago
- ☆26Updated 2 years ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆28Updated 2 years ago
- This is the documentation of the Tensorflow/Keras implementation of Latent Backdoor Attacks. Please see the paper for details Latent Back…☆19Updated 3 years ago