Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
By Kaidi Xu, Zhouxing Shi, Huan Zhang, Yihan Wang, Kai-Wei Chang, Minlie Huang, Bhavya Kailkhura, Xue Lin, Cho-Jui Hsieh. Neural Information Processing Systems, 2020
389 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/18a9bb863e3110e2e981b53618b214585a32f877
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification (2021, methodology): “Xu et al. [44] used CROWN as a massively paralleled incomplete solver on GPUs for complete verification, but it cannot handle neuron split constraints, leading to suboptimal efficiency and high timeout rates.”
- On Robust Prefix-Tuning for Text Classification (2022, background): “…including model functional improvement (Li & Sethy, 2019; Jones et al., 2020), certification (Jia et al., 2019; Huang et al., 2019; Shi et al., 2020; Xu et al., 2020; Ye et al., 2020), adversary detection (Pruthi et al., 2019; Zhou et al., 2019), and adversarial training (Miyato et al., 2017; 2019;…”
- Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation (2023, background): “This umbrella of oversight - commonly referred to as ’alignment’ - remains a hot topic for research (Xu et al., 2020; Ouyang et al., 2022; Bai et al., 2022b; Go et al., 2023; Korbak et al., 2023).”