2018 - IEEE Fellow For contributions to the application of formal methods to security
2016 - ACM Fellow For contributions to verification, programming languages, and software engineering.
2014 - ACM Distinguished Member
Somesh Jha spends much of his time researching Theoretical computer science, Computer security, Model checking, Malware and Data mining. His Theoretical computer science study integrates concerns from other disciplines, such as Finite-state machine, Algorithm, Programming language and State. In his study, which falls under the umbrella issue of Computer security, Blacklist, Spoofing attack and Computer network is strongly linked to The Internet.
His work deals with themes such as Distributed computing, Cryptography, Temporal logic, Boolean function and Binary decision diagram, which intersect with Model checking. The Malware study combines topics in areas such as Adversarial system, Adversary and Machine learning, Deep learning. His Data mining research is multidisciplinary, incorporating perspectives in Process, Set, Cluster analysis, Exploit and Estimation.
His scientific interests lie mostly in Theoretical computer science, Computer security, Artificial intelligence, Data mining and Adversarial system. Somesh Jha focuses mostly in the field of Theoretical computer science, narrowing it down to topics relating to Algorithm and, in certain cases, DFA minimization. His work in Malware, Intrusion detection system, Computer security model, Security service and Cryptography is related to Computer security.
In most of his Artificial intelligence studies, his work intersects topics such as Machine learning. Data mining connects with themes related to Signature in his study. Somesh Jha has researched Model checking in several fields, including Distributed computing, State space and Temporal logic.
His main research concerns Artificial intelligence, Artificial neural network, Robustness, Adversarial system and Theoretical computer science. Somesh Jha interconnects Machine learning and Key in the investigation of issues within Artificial intelligence. His Robustness research incorporates themes from Discrete mathematics and Adversary.
His Adversarial system research includes themes of Class, Pixel and Statistical classification. Somesh Jha has included themes like Space, Differential privacy and Dimension in his Theoretical computer science study. His research in Adversarial machine learning intersects with topics in Contextual image classification and Computer security.
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Differential privacy, Robustness and Artificial neural network. His work on Adversarial system, Deep learning and Inference as part of general Artificial intelligence study is frequently linked to Attribution, therefore connecting diverse disciplines of science. His Machine learning research includes elements of Clinical decision support system and Training set.
As a part of the same scientific family, Somesh Jha mostly works in the field of Differential privacy, focusing on Server and, on occasion, Distributed computing, Class, Software framework and Encryption. In his research, Encoding, Adversary and Code is intimately related to Theoretical computer science, which falls under the overarching field of Robustness. His study in Artificial neural network is interdisciplinary in nature, drawing from both Time complexity, Statistical classification and Cryptography.
This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.
The Limitations of Deep Learning in Adversarial Settings
Nicolas Papernot;Patrick McDaniel;Somesh Jha;Matt Fredrikson.
ieee european symposium on security and privacy (2016)
Automated generation and analysis of attack graphs
O. Sheyner;J. Haines;S. Jha;R. Lippmann.
ieee symposium on security and privacy (2002)
Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks
Nicolas Papernot;Patrick McDaniel;Xi Wu;Somesh Jha.
ieee symposium on security and privacy (2016)
Practical Black-Box Attacks against Machine Learning
Nicolas Papernot;Patrick McDaniel;Ian Goodfellow;Somesh Jha.
computer and communications security (2017)
Counterexample-guided abstraction refinement for symbolic model checking
Edmund Clarke;Orna Grumberg;Somesh Jha;Yuan Lu.
Journal of the ACM (2003)
Semantics-aware malware detection
M. Christodorescu;S. Jha;S.A. Seshia;D. Song.
ieee symposium on security and privacy (2005)
Static analysis of executables to detect malicious patterns
Mihai Christodorescu;Somesh Jha.
usenix security symposium (2003)
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Matt Fredrikson;Somesh Jha;Thomas Ristenpart.
computer and communications security (2015)
Two formal analyses of attack graphs
S. Jha;O. Sheyner;J. Wing.
ieee computer security foundations symposium (2002)
Modular verification of software components in C
S. Chaki;E.M. Clarke;A. Groce;S. Jha.
IEEE Transactions on Software Engineering (2004)
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: