An official website of the United States government
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
Feasibility Prediction for Rapid IC Design Space Exploration
The DARPA POSH program echoes with the research community and identifies that engineering productivity has fallen behind Moore’s law, resulting in the prohibitive increase in IC design cost at leading technology nodes. The primary reason is that it requires many computing resources, expensive tools, and even many days to complete a design implementation. However, at the end of this process, some designs could not meet the design constraints and become unroutable, creating a vicious circuit design cycle. As a result, designers have to re-run the whole process after design modification. This research applied a machine learning approach to automatically identify design constraints and design rule checking (DRC) violation issues and help the designer identify design constraints with optimal DRCs before the long detailed routing process through iterative greedy search. The proposed algorithm achieved up to 99.99% design constraint prediction accuracy and reduced 98.4% DRC violations with only a 6.9% area penalty.
more »
« less
- Award ID(s):
- 2138253
- PAR ID:
- 10376243
- Date Published:
- Journal Name:
- Electronics
- Volume:
- 11
- Issue:
- 7
- ISSN:
- 2079-9292
- Page Range / eLocation ID:
- 1161
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Historically, teachers’ uptake and implementation of empirically supported classroom interventions have involved substantial face-to-face consultation. However, most schools do not have the resources to provide this intensive level of support and many teachers may not need it. Thus, evaluation of alternative supports is warranted. In this pilot study, we evaluated the feasibility and effectiveness of an interactive web-based technology [i.e., the Daily Report Card.Online (DRC.O)] designed to facilitate teachers’ use of the DRC with minimal external support and examined individual teacher characteristics associated with DRC use. Elementary school teachers (N = 54) were given access to the DRC.O Web site and asked to use it to implement a DRC with one child. With regard to implementation, 16% were short-term adopters (less than 1 month) and 39% were long-term adopters (1–7 months of use). On average, short-term adopters adhered to 37% of data entry procedures, whereas long-term adopters adhered to 74% of data entry procedures. Higher teacher stress was associated with shorter use and lower adherence. Web site analytics revealed that, on average, long-term adopters completed all steps of DRC development in less than 1 h and spent only 3 min per day engaged in data entry for progress monitoring. The magnitude of change in student target behaviors and Strengths and Difficulties Questionnaire scores was moderate to large. These results reveal the feasibility and promise of the DRC.O and generate hypotheses for future research. Implications for additional evaluation of technology-driven implementation supports for teachers are discussed.more » « less
-
Reverse engineering (RE) in Integrated Circuits (IC) is a process in which one will attempt to extract the internals of an IC, extract the circuit structure, and determine the gate-level information of an IC. In general, the RE process can be done for validation as well as Intellectual Property (IP) stealing intentions. In addition, RE also facilitates different illicit activities such as the insertion of hardware Trojan, pirating, or counterfeiting a design, or developing an attack. In this work, we propose an approach to introduce cognitive perturbations, with the aid of adversarial machine learning, to the IC layout that could prevent the RE process from succeeding. We first construct a layer-by-layer image dataset of 45 nm predictive technology. With this dataset, we propose a conventional neural network model called RecoG-Net to recognize the logic gates, which is the first step in RE. RecoG-Net is successful in recognizing the gates with more than 99.7% accuracy. Our thwarting approach utilizes the concept of adversarial attack generation algorithms to generate perturbation. Unlike traditional adversarial attacks in machine learning, the perturbation generation needs to be highly constrained to meet the fab rules such as Design Rule Checking (DRC) Layout vs. Schematic (LVS) checks. Hence, we propose CAPTIVE as a constrained perturbation generation satisfying the DRC. The experiments show that the accuracy of reverse engineering using machine learning techniques can decrease from 100% to approximately 30% based on the adversary generator.more » « less
-
We present Deep Region Competition (DRC), an algorithm designed to extract foreground objects from images in a fully unsupervised manner. Foreground extraction can be viewed as a special case of generic image segmentation that focuses on identifying and disentangling objects from the background. In this work, we rethink the foreground extraction by reconciling energy-based prior with generative image modeling in the form of Mixture of Experts (MoE), where we further introduce the learned pixel re-assignment as the essential inductive bias to capture the regularities of background regions. With this modeling, the foreground/background partition can be naturally found through Expectation-Maximization (EM). We show that the proposed method effectively exploits the interaction between the mixture components during the partitioning process, which closely connects to region competition, a seminal approach for generic image segmentation. Experiments demonstrate that DRC exhibits more competitive performances on complex real-world data and challenging multi-object scenes compared with prior methods. Moreover, we show empirically that DRC can potentially generalize to novel foreground objects even from categories unseen during training.more » « less
-
null (Ed.)Additive manufacturing, also known as 3D printing, is commonly shown to students through low cost 3D printers. Many high school and community college educators have access to 3D printers at their home institutions. In this study, Research Experience for Teachers (RET) participants developed a set of modules which can be integrated with a design project given at both the high school and college curriculum levels to explore the concepts of manufacturing and design (e.g., dimensioning and tolerancing, Design for X, Proof of Concept, etc.). The study identified a product in which these concepts can be integrated, and developed a set of constraints the students need to consider in their design project. It was the goal of the RET participants to identify best practices for teaching 3D printing and develop projects to explain design and manufacturing concepts through 3D printing.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/electronics11071161
