Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
AircraftVerse: a large-scale multimodal dataset of aerial vehicle designs
- Adam D. Cobb,
- Anirban Roy,
- Daniel Elenius,
- F. Michael Heim,
- Brian Swenson,
- Sydney Whittington,
- James D. Walker,
- Theodore Bapty,
- Joseph Hite,
- Karthik Ramani,
- Christopher McComb,
- Susmit Jha
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 1928, Pages 44524–44543We present AircraftVerse, a publicly available aerial vehicle design dataset. Aircraft design encompasses different physics domains and, hence, multiple modalities of representation. The evaluation of these cyber-physical system (CPS) designs requires ...
CODiT: Conformal Out-of-Distribution Detection in Time-Series Data for Cyber-Physical Systems
- Ramneet Kaur,
- Kaustubh Sridhar,
- Sangdon Park,
- Yahan Yang,
- Susmit Jha,
- Anirban Roy,
- Oleg Sokolsky,
- Insup Lee
ICCPS '23: Proceedings of the ACM/IEEE 14th International Conference on Cyber-Physical Systems (with CPS-IoT Week 2023)Pages 120–131https://doi.org/10.1145/3576841.3585931Uncertainty in the predictions of learning enabled components hinders their deployment in safety-critical cyber-physical systems (CPS). A shift from the training distribution of a learning enabled component (LEC) is one source of uncertainty in the LEC's ...
- research-articleMarch 2024
Principled out-of-distribution detection via multiple testing
The Journal of Machine Learning Research (JMLR), Volume 24, Issue 1Article No.: 378, Pages 18118–18152We study the problem of out-of-distribution (OOD) detection, that is, detecting whether a machine learning (ML) model's output can be trusted at inference time. While a number of tests for OOD detection have been proposed in prior work, a formal ...
-
- research-articleDecember 2021
MISA: Online Defense of Trojaned Models using Misattributions
ACSAC '21: Proceedings of the 37th Annual Computer Security Applications ConferencePages 570–585https://doi.org/10.1145/3485832.3485908Recent studies have shown that neural networks are vulnerable to Trojan attacks, where a network is trained to respond to specially crafted trigger patterns in the inputs in specific and potentially malicious ways. This paper proposes MISA, a new online ...
- ArticleSeptember 2020
Model-Centered Assurance for Autonomous Systems
AbstractThe functions of an autonomous system can generally be partitioned into those concerned with perception and those concerned with action. Perception builds and maintains an internal model of the world (i.e., the system’s environment) that is used ...
- research-articleNovember 2020
TrojDRL: evaluation of backdoor attacks on deep reinforcement learning
DAC '20: Proceedings of the 57th ACM/EDAC/IEEE Design Automation ConferenceArticle No.: 31, Pages 1–6We present TrojDRL, a tool for exploring and evaluating backdoor attacks on deep reinforcement learning agents. TrojDRL exploits the sequential nature of deep reinforcement learning (DRL) and considers different gradations of threat models. We show that ...
- ArticleMay 2020
Correction to: NASA Formal Methods
The original versions of this book and Chapter 14 were revised. The following was corrected:
Dimitra Giannakopoulou, the General Chair of the NFM 2020 conference, was inadvertently forgotten and, therefore, added as a volume editor.
Chapter 14 was ...
- research-articleDecember 2019
Attribution-based confidence metric for deep neural networks
- Susmit Jha,
- Sunny Raj,
- Steven Lawrence Fernandes,
- Sumit Kumar Jha,
- Somesh Jha,
- Brian Jalaian,
- Gunjan Verma,
- Ananthram Swami
NIPS'19: Proceedings of the 33rd International Conference on Neural Information Processing SystemsDecember 2019, Article No.: 1060, Pages 11837–11848We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric characterizes whether the output of a DNN on an input can be trusted. DNNs are known to be brittle on inputs outside the training ...
- research-articleDecember 2019
Explaining AI Decisions Using Efficient Methods for Learning Sparse Boolean Formulae
Journal of Automated Reasoning (JAUR), Volume 63, Issue 4Pages 1055–1075https://doi.org/10.1007/s10817-018-9499-8AbstractIn this paper, we consider the problem of learning Boolean formulae from examples obtained by actively querying an oracle that can label these examples as either positive or negative. This problem has received attention in both machine learning as ...
- ArticleJuly 2019
Trust, Resilience and Interpretability of AI Models
AbstractIn this tutorial, we present our recent work on building trusted, resilient and interpretable AI models by combining symbolic methods developed for automated reasoning with connectionist learning methods that use deep neural networks. The ...
- demonstrationApril 2019
Sherlock - A tool for verification of neural network feedback systems: demo abstract
HSCC '19: Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and ControlPages 262–263https://doi.org/10.1145/3302504.3313351We present an approach for the synthesis and verification of neural network controllers for closed loop dynamical systems, modelled as an ordinary differential equation. Feedforward neural networks are ubiquitous when it comes to approximating functions,...
- ArticleDecember 2018
Learning task specifications from demonstrations
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsPages 5372–5382Real-world applications often naturally decompose into several sub-tasks. In many settings (e.g., robotics) demonstrations provide a natural way to specify the sub-tasks. However, most methods for learning from demonstrations either do not provide ...
- research-articleNovember 2018
Toward an Internet of Battlefield Things: A Resilience Perspective
- Tarek Abdelzaher,
- Nora Ayanian,
- Tamer Basar,
- Suhas Diggavi,
- Jana Diesner,
- Deepak Ganesan,
- Ramesh Govindan,
- Susmit Jha,
- Tancrede Lepoint,
- Benjamin Marlin,
- Klara Nahrstedt,
- David Nicol,
- Raj Rajkumar,
- Stephen Russell,
- Sanjit Seshia,
- Fei Sha,
- Prashant Shenoy,
- Mani Srivastava,
- Gaurav Sukhatme,
- Ananthram Swami,
- Paulo Tabuada,
- Don Towsley,
- Nitin Vaidya,
- Venu Veeravalli
The Internet of Battlefield Things (IoBT) might be one of the most expensive cyber-physical systems of the next decade, yet much research remains to develop its fundamental enablers. A challenge that distinguishes the IoBT from its civilian counterparts ...
- research-articleOctober 2018
Detecting Adversarial Examples Using Data Manifolds
MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM)Pages 547–552https://doi.org/10.1109/MILCOM.2018.8599691Models produced by machine learning, particularly deep neural networks, are state-of-the-art for many machine learning tasks and demonstrate very high prediction accuracy. Unfortunately, these models are also very brittle and vulnerable to specially ...
- articleJanuary 2018
Safe Autonomy Under Perception Uncertainty Using Chance-Constrained Temporal Logic
Journal of Automated Reasoning (JAUR), Volume 60, Issue 1Pages 43–62https://doi.org/10.1007/s10817-017-9413-9Autonomous vehicles have found wide-ranging adoption in aerospace, terrestrial as well as marine use. These systems often operate in uncertain environments and in the presence of noisy sensors, and use machine learning and statistical sensor fusion ...
- articleNovember 2017
A theory of formal synthesis via inductive learning
Formal synthesis is the process of generating a program satisfying a high-level formal specification. In recent times, effective formal synthesis methods have been proposed based on the use of inductive learning. We refer to this class of methods that ...