yjkim721 / STRIP-ViTALinks
This work corroborates a run-time Trojan detection method exploiting STRong Intentional Perturbation of inputs, is a multi-domain Trojan detection defence across Vision, Text and Audio domains---thus termed as STRIP-ViTA. Specifically, STRIP-ViTA is the first confirmed Trojan detection method that is demonstratively independent of both the task …
☆10Updated 4 years ago
Alternatives and similar repositories for STRIP-ViTA
Users that are interested in STRIP-ViTA are comparing it to the libraries listed below
Sorting:
- ☆19Updated 4 years ago
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆27Updated 5 years ago
- [CVPR 2022] "Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free" by Tianlong Chen*, Zhenyu Zhang*, Yihua Zhang*, Shiyu C…☆26Updated 2 years ago
- ☆25Updated 2 years ago
- [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…☆15Updated last year
- This is the code repo of our Pattern Recognition journal on IPR protection of Image Captioning Models☆11Updated 2 years ago
- Codes for the ICLR 2022 paper: Trigger Hunting with a Topological Prior for Trojan Detection☆11Updated 2 years ago
- Official Repository for the CVPR 2020 paper "Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs"☆43Updated last year
- The official pytorch implementation of ACM MM 19 paper "MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks"☆11Updated 4 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- ☆15Updated 2 years ago
- Pytorch implementation of NPAttack☆12Updated 5 years ago
- A repository for the query-efficient black-box attack, SignHunter☆23Updated 5 years ago
- ☆19Updated 4 years ago
- Code for identifying natural backdoors in existing image datasets.☆15Updated 3 years ago
- Code for "Neuron Shapley: Discovering the Responsible Neurons"☆27Updated last year
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆20Updated 2 years ago
- ☆11Updated 3 years ago
- ☆11Updated 3 years ago
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Updated 3 years ago
- ☆24Updated 2 years ago
- ReColorAdv and other attacks from the NeurIPS 2019 paper "Functional Adversarial Attacks"☆38Updated 3 years ago
- ☆11Updated 2 years ago
- ☆23Updated 6 years ago
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆32Updated 2 years ago
- This is the source code for HufuNet. Our paper is accepted by the IEEE TDSC.☆22Updated 2 years ago
- kyleliang919 / Uncovering-the-Connections-BetweenAdversarial-Transferability-and-Knowledge-Transferabilitycode for ICML 2021 paper in which we explore the relationship between adversarial transferability and knowledge transferability.☆17Updated 2 years ago
- ☆19Updated 3 years ago
- competition☆17Updated 5 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Updated 5 years ago