What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Operating system
- Machine learning
Pavel Laskov mainly investigates Artificial intelligence, Machine learning, Support vector machine, Classifier and Training set.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Data mining and Malware.
His Malware study combines topics in areas such as Software and Discriminative model.
His work on Interpretability and Kernel as part of general Machine learning research is frequently linked to Linear combination and Lp space, bridging the gap between disciplines.
His work deals with themes such as Adversary and Intrusion detection system, which intersect with Support vector machine.
His Intrusion detection system study incorporates themes from Semi-supervised learning and Pattern recognition.
His most cited work include:
- Evasion attacks against machine learning at test time (939 citations)
- Learning and Classification of Malware Behavior (458 citations)
- Poisoning Attacks against Support Vector Machines (380 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Machine learning, Intrusion detection system, Anomaly detection and Computer security.
His work in Artificial intelligence is not limited to one particular discipline; it also encompasses Pattern recognition.
His studies in Machine learning integrate themes in fields like Adversarial system and Adversary.
His Anomaly detection research incorporates elements of Security analysis, Supervised learning and False positive paradox.
A large part of his Computer security studies is devoted to Malware.
He usually deals with Support vector machine and limits it to topics linked to Training set and Gradient descent and Data manipulation language.
He most often published in these fields:
- Artificial intelligence (53.52%)
- Machine learning (30.99%)
- Intrusion detection system (29.58%)
What were the highlights of his more recent work (between 2010-2017)?
- Artificial intelligence (53.52%)
- Machine learning (30.99%)
- Classifier (9.86%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Machine learning, Classifier, Support vector machine and Malware.
He interconnects Consistency and Optimization problem in the investigation of issues within Artificial intelligence.
His studies deal with areas such as Adversarial system, Computer security, Adversary and Cryptovirology as well as Machine learning.
His research investigates the connection between Adversary and topics such as Statistical classification that intersect with problems in Adversarial machine learning and Artificial neural network.
His Support vector machine research integrates issues from Training set and Kernel.
His Malware research incorporates themes from Exploit, Information security, Effective method and Data mining.
Between 2010 and 2017, his most popular works were:
- Evasion attacks against machine learning at test time (939 citations)
- Poisoning Attacks against Support Vector Machines (380 citations)
- Poisoning Attacks against Support Vector Machines (270 citations)
In his most recent research, the most cited papers focused on:
- Operating system
- Artificial intelligence
- Machine learning
Pavel Laskov spends much of his time researching Machine learning, Artificial intelligence, Support vector machine, Classifier and Training set.
His study deals with a combination of Machine learning and Pre-play attack.
Pavel Laskov integrates several fields in his works, including Pre-play attack, Statistical classification, Computer security, Artificial neural network and Adversarial machine learning.
His Artificial intelligence research is multidisciplinary, relying on both Adversary and Malware.
The Learning based study combines topics in areas such as Feature extraction and Data mining.
Many of his studies on Intrusion detection system involve topics that are commonly interrelated, such as Data manipulation language.
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.
