More Like this

1. AI/ML curation of AI/ML training datasets

   https://doi.org/10.1117/12.3055515  

   Shukla, Shruti; Pados, Dimitris A; Varma, Kavita; Sklivanitis, George; Bentley, Elizabeth S; Medley, Michael J (May 2025, SPIE)

   Sklivanitis, George; Markopoulos, Panagiotis; Ouyang, Bing (Ed.)
2. GEVO-ML: a proposal for optimizing ML code with evolutionary computation

   https://doi.org/10.1145/3377929.3398139  

   Liou, Jhe-Yu; Wang, Xiaodong; Forrest, Stephanie; Wu, Carole-Jean (July 2020, GECCO Companion)
3. ML Field Planner: Analyzing and Optimizing ML Pipelines For Field Research

   https://doi.org/10.1145/3708035.3736013  

   Stubbs, Joe; Balasubramaniam, Sowbaranika; Khuvis, Samuel; Withana, Sachith; Vallabhajosyula, Manikya Swathi; Cardone, Richard; Garcia, Christian; Freeman, Nathan; Guzman, Carlos; Plale, Beth; et al (July 2025, ACM)
4. ponder-lab/ML: 0.34.0

   https://doi.org/10.5281/zenodo.7992107  

   Khatchadourian, Raffi; Dolby, Julian; Vélez, Tatiana Castro; shinnar; Lagouvardos, Sifis; Sridharan, Manu (January 2024, Zenodo)

   Full Changelog: https://github.com/ponder-lab/ML/compare/0.33.0...0.34.0 

   more » « less
5. Robustify ML-Based Lithography Hotspot Detectors

   https://doi.org/10.1145/3508352.3549389  

   Pan, Jingyu; Chang, Chen-Chia; Xie, Zhiyao; Hu, Jiang; Chen, Yiran (October 2022, 2022 IEEE/ACM International Conference On Computer Aided Design (ICCAD))

   Deep learning has been widely applied in various VLSI design automation tasks, from layout quality estimation to design optimization. Though deep learning has shown state-of-the-art performance in several applications, recent studies reveal that deep neural networks exhibit intrinsic vulnerability to adversarial perturbations, which pose risks in the ML-aided VLSI design flow. One of the most effective strategies to improve robustness is regularization approaches, which adjust the optimization objective to make the deep neural network generalize better. In this paper, we examine several adversarial defense methods to improve the robustness of ML-based lithography hotspot detectors. We present an innovative design rule checking (DRC)-guided curvature regularization (CURE) approach, which is customized to robustify ML-based lithography hotspot detectors against white-box attacks. Our approach allows for improvements in both the robustness and the accuracy of the model. Experiments show that the model optimized by DRC-guided CURE achieves the highest robustness and accuracy compared with those trained using the baseline defense methods. Compared with the vanilla model, DRC-guided CURE decreases the average attack success rate by 53.9% and increases the average ROC-AUC by 12.1%. Compared with the best of the defense baselines, DRC-guided CURE reduces the average attack success rate by 18.6% and improves the average ROC-AUC by 4.3%. 

   more » « less