naiyeleo / ABS
ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation
☆47Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for ABS
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆49Updated 5 years ago
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)☆46Updated 6 years ago
- ☆76Updated 3 years ago
- This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks…☆118Updated 2 years ago
- Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems☆24Updated 3 years ago
- ☆62Updated 4 years ago
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆69Updated 6 years ago
- This is the implementation for CVPR 2022 Oral paper "Better Trigger Inversion Optimization in Backdoor Scanning."☆24Updated 2 years ago
- Code for the paper: Label-Only Membership Inference Attacks☆64Updated 3 years ago
- [IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks☆17Updated last month
- Code for ML Doctor☆86Updated 2 months ago
- ☆25Updated 2 years ago
- Input-aware Dynamic Backdoor Attack (NeurIPS 2020)☆27Updated 3 months ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆50Updated last year
- ☆24Updated last year
- [AAAI'21] Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification☆28Updated 4 months ago
- ☆17Updated 2 years ago
- ☆19Updated 4 years ago
- ☆10Updated 3 years ago
- Anti-Backdoor learning (NeurIPS 2021)☆78Updated last year
- A minimal PyTorch implementation of Label-Consistent Backdoor Attacks☆27Updated 3 years ago
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆28Updated 2 years ago
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks☆17Updated 5 years ago
- Code for "Label-Consistent Backdoor Attacks"☆49Updated 3 years ago
- Code for "Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment" (CCS 2019)☆46Updated 4 years ago
- Code release for DeepJudge (S&P'22)☆51Updated last year
- WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)☆111Updated 3 months ago
- [IEEE S&P'24] ODSCAN: Backdoor Scanning for Object Detection Models☆11Updated 4 months ago
- Invisible Backdoor Attack with Sample-Specific Triggers☆88Updated 2 years ago
- ☆23Updated 2 years ago