1. Transferable Clean-Label Poisoning Attacks on Deep Neural Nets;zhu;Proc of the International Conference on Machine Learning (ICML),0
2. Trojaning Language Models for Fun and Profit;zhang;ArXiv e-prints,2020
3. Interpretable Deep Learning under Fire;zhang;Proceedings of USENIX Security Symposium (SEC),0
4. How Transferable Are Features in Deep Neural Networks?;yosinski;Proceedings of Advances in Neural Information Processing Systems (NeurIPS),0
5. Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks