Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Search Publications by: Apostol Vassilev (Fed)

Search Title, Abstract, Conference, Citation, Keyword or Author
Displaying 1 - 23 of 23

Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations

January 4, 2024
Author(s)
Apostol Vassilev, Alina Oprea, Alie Fordyce, Hyrum Andersen
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

Poisoning Attacks against Machine Learning: Can Machine Learning be Trustworthy?

October 24, 2022
Author(s)
Alina Oprea, Anoop Singhal, Apostol Vassilev
Many practical applications benefit from Machine Learning (ML) and Artificial Intelligence (AI) technologies, but their security needs to be studied in more depth before the methods and algorithms are actually deployed in critical settings. In this article

Towards a Standard for Identifying and Managing Bias in Artificial Intelligence

March 15, 2022
Author(s)
Reva Schwartz, Apostol Vassilev, Kristen K. Greene, Lori Perine, Andrew Burt, Patrick Hall
As individuals and communities interact in and with an environment that is increasingly virtual they are often vulnerable to the commodification of their digital exhaust. Concepts and behavior that are ambiguous in nature are captured in this environment

NIST Roadmap Toward Criteria for Threshold Schemes for Cryptographic Primitives

July 7, 2020
Author(s)
Luis Brandao, Michael S. Davidson, Apostol T. Vassilev
This document constitutes a preparation toward devising criteria for the standardization of threshold schemes for cryptographic primitives by the National Institute of Standards and Technology (NIST). The large diversity of possible threshold schemes, as

Leveraging Side-channel Information for Disassembly and Security

February 1, 2020
Author(s)
JUNGMIN Park, Fahim Rahman, Apostol Vassilev, Domenic Forte, Mark Tehranipoor
With the rise of Internet of Things (IoT), devices such as smartphones, embedded medical devices, smart home appliances as well as traditional computing platforms such as personal computers and servers have been increasingly targeted with a variety of

BowTie - a deep learning feedforward neural network for sentiment analysis

January 3, 2020
Author(s)
Apostol T. Vassilev
How to model and encode the semantics of human-written text and select the type of neural network to process it are not settled issues in sentiment analysis. Accuracy and transferability are critical issues in machine learning in general. These properties

RTL-PSC: Automated Power Side-Channel Leakage Assessment at Register-Transfer Level

July 11, 2019
Author(s)
Miao (Tony) He, Jungmin Park, Adib Nahiyan, Apostol Vassilev, Yier Jin, Mark Tehranipoor
Power side-channel attacks (SCAs) have become a major concern to the security community due to their non- invasive feature, low-cost, and effectiveness in extracting secret information from hardware implementation of cryto algorithms. Therefore, it is

Electronics Supply Chain Integrity Enabled by Blockchain

June 1, 2019
Author(s)
Xiaolin Xu, Fahim Rahman, Bicky Shakya, Apostol Vassilev, Domenic Forte, Mark Tehranipoor
Electronic systems are ubiquitous today, playing an irreplaceable role in our personal lives as well as in critical infrastructures such as power grid, satellite communication, and public transportation. In the past few decades, the security of software

BowTie - A deep learning feedforward neural network for sentiment analysis

April 22, 2019
Author(s)
Apostol T. Vassilev
How to model and encode the semantics of human-written text and select the type of neural network to process it with are not settled issues in sentiment analysis. Accuracy and transferability are critical issues in machine learning in general. These

Time to Standardize Threshold Schemes for Cryptographic Primitives

April 10, 2019
Author(s)
Luis Brandao, Michael S. Davidson, Nicky W. Mouha, Apostol T. Vassilev
This bulletin summarizes the information found in NISTIR 8214: Threshold Schemes for Cryptographic Primitives. NIST is interested in promoting the security of implementations of cryptographic primitives. This security depends not only on the theoretical

Threshold Schemes for Cryptographic Primitives

March 1, 2019
Author(s)
Luis T. A. N. Brandao, Nicky W. Mouha, Apostol T. Vassilev
The Computer Security Division at the National Institute of Standards and Technology is interested in promoting the security of implementations of cryptographic primitives. This security depends not only on the theoretical properties of the primitives but

Automated Cryptographic Validation (ACV) Testing

September 24, 2018
Author(s)
Apostol T. Vassilev, Larry Feldman, Gregory A. Witte
This bulletin summarizes the NIST Automated Cryptographic Validation (ACV) Testing project. NIST selects and standardizes cryptographic algorithms as NIST-approved for use within the U.S. Federal Government. The Computer Security Division specifies the

Psst, Can you Keep a Secret?

January 2, 2018
Author(s)
Apostol T. Vassilev, Nicky W. Mouha, Luis T. A. N. Brandao
The security of encrypted data depends not only on the theoretical properties of cryptographic primitives but also on the robustness of their implementations in software and hardware. Threshold cryptography introduces a computational paradigm that enables

Entropy as a Service: Unlocking Cryptography's Full Potential

September 7, 2016
Author(s)
Apostol T. Vassilev, Robert L. Staples
Securing the Internet of Things (IoT) requires strong cryptography, which depends on the availability of good entropy for generating unpredictable keys and accurate clocks. Attacks abusing weak keys or old inputs portend challenges for IoT. EaaS is a novel

Cryptographic Module Validation Program (CMVP)

December 1, 2014
Author(s)
Apostol T. Vassilev, Larry Feldman, Gregory A. Witte
The Cryptographic Module Validation Program (CMVP) validates cryptographic modules for compliance with Federal Information Processing Standard (FIPS) Publication 140-2, Security Requirements for Cryptographic Modules, and other cryptography based standards

The Importance of Entropy to Information Security

February 3, 2014
Author(s)
Apostol T. Vassilev, Timothy Hall
The strength of cryptographic keys is an active challenge in academic research and industrial practice. In this paper we discuss the entropy as fundamentally important concept for generating hard-to-guess, i.e., strong, cryptographic keys and outline the