Apostol Vassilev

Apostol Vassilev

Auto-generated profile, based on publicly available information

Apostol Vassilev

National Institute of Standards and Technology

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 January 2024
Verified
Report
Closed access
AVApostol Vassilev
Apostol Vassilev
AOAlina Oprea
Alina Oprea
AFAlie Fordyce
Alie Fordyce
HAHyrum Anderson
Hyrum Anderson
This NIST AI report develops a taxonomy of concepts and defines terminology in the field of adversarial machine learning (AML). The taxonomy is built on survey of the AML literature and is arranged in a conceptual hierarchy that includes key types of ML methods and lifecycle stage of attack, attacker goals and objectives, and attacker capabilities and knowledge of the learning process. The report also provides corresponding methods for mitigating and managing the consequences of attacks and points out relevant open challenges to take into account in the lifecycle of AI systems. The terminology used in the report is consistent with the literature on AML and is complemented by a glossary that defines key terms associated with the security of AI systems and is intended to assist non-expert readers. Taken together, the taxonomy and terminology are meant to inform other standards and future practice guides for assessing and managing the security of AI systems, by establishing a common language and understanding of the rapidly developing AML landscape.

8 March 2023
Verified
Report
Closed access
AOAlina Oprea
Alina Oprea
AVApostol Vassilev
Apostol Vassilev
This NIST AI report develops a taxonomy of concepts and defines terminology in the field of adversarial machine learning (AML). The taxonomy is built on survey of the AML literature and is arranged in a conceptual hierarchy that includes key types of ML methods and lifecycle stage of attack, attacker goals and objectives, and attacker capabilities and knowledge of the learning process. The report also provides corresponding methods for mitigating and managing the consequences of attacks and points out relevant open challenges to take into account in the lifecycle of AI systems. The terminology used in the report is consistent with the literature on AML and is complemented by a glossary that defines key terms associated with the security of AI systems and is intended to assist non-expert readers. Taken together, the taxonomy and terminology are meant to inform other standards and future practice guides for assessing and managing the security of AI systems, by establishing a common language and understanding of the rapidly developing AML landscape.

25 October 2022 in Computer
Verified
Journal Article
Closed access
AOAlina Oprea
Alina Oprea
ASAnoop Singhal
Anoop Singhal
AVApostol Vassilev
Apostol Vassilev
Many practical applications benefit from machine learning and artificial intelligence technologies, but their security needs to be studied in more depth. We discuss the risk of poisoning attacks against the training stage of machine learning and challenges of defending against them.

13 December 2021 in IEEE Design & Test
Verified
Journal Article
Closed access
JHJiaji He
Jiaji He
XGXiaolong Guo
Xiaolong Guo
MTMark Tehranipoor
Mark Tehranipoor
AVApostol Vassilev
Apostol Vassilev
YJYier Jin
Yier Jin
Side channels are present in all systems, including digital ones. This article analyzes electromagnetic side channels from both the attack and defense perspectives.

26 July 2024
Verified
Report
Closed access
MSMurugiah Souppaya
Murugiah Souppaya
AVApostol Vassilev
Apostol Vassilev
MOMichael Ogata
Michael Ogata
MSMartin Stanley
Martin Stanley
KSKaren Scarfone
Karen Scarfone

4 June 2024
Verified
Report
Closed access
ZKZeid Suzanne Kootbally
Zeid Suzanne Kootbally
PRPrem Rachakonda
Prem Rachakonda
SLSuzanne Lightman
Suzanne Lightman
AVApostol Vassilev
Apostol Vassilev
DWDavid A Wollman
David A Wollman
EGEdward Griffor
Edward Griffor
On September 5–8, 2023, the National Institute of Standards and Technology (NIST) held the second Standards and Performance Metrics for On‐Road Automated Vehicles Workshop. This four‐day virtual event provided updates on NIST’s recent work in automated vehicles (AVs) and gave stakeholders an opportunity to provide feedback and input on current and future NIST research. The workshop included high‐level keynote presentations, a series of industry keynote presentations, and NIST presentations on its current AV activities. The industry keynotes and NIST presentations were paired with breakout sessions that discussed NIST’s progress, community challenges, and stakeholder research needs in six key areas: systems interaction, perception, cybersecurity, communications, artificial intelligence, and digital infrastructure. There was general agreement that developing standards allows for better comparisons and evaluations of emerging technologies. Other key themes included: 1) Digital technologies for automation and related security/privacy concerns, including artificial intelligence, machine learning, and smart communication technologies (i.e., vehicle‐to‐vehicle (V2V), vehicle‐to‐infrastructure (V2I), and vehicle‐to‐everything (V2X)), 2) Need for standardized or common language to improve information sharing, 3) Open data sets to support and validate technical advances and standardization across system components and areas (i.e., standards evolving in parallel with technology), and 4) Pivotal role for NIST as a convener to bring diverse stakeholders together for knowledge exchange and cross‐industry dialogue.