James Mickens

James Mickens

Auto-generated profile, based on publicly available information

James Mickens

Harvard University, Cambridge, MA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
22 April 2024
Verified
Conference Paper
Open access
YZYang Zhou
Yang Zhou
MWMark Wilkening
Mark Wilkening
JMJames Mickens
James Mickens
MYMinlan Yu
Minlan Yu

19 November 2025
Verified
Conference Paper
Open access
DIDavid Inyangson
David Inyangson
SRSarah Radway
Sarah Radway
TJTushar M. Jois
Tushar M. Jois
NFNelly Fazio
Nelly Fazio
JMJames Mickens
James Mickens

21 February 2026 in ACM Computing Surveys
Verified
Journal Article
Open access
JHJacob Huckelberry
Jacob Huckelberry
YZYuke Zhang
Yuke Zhang
ASAllison Sansone
Allison Sansone
JMJames Mickens
James Mickens
PBPeter Anthony Beerel
Peter Anthony Beerel
VRVijay Janapa Reddi
Vijay Janapa Reddi
Tiny Machine Learning (TinyML) enables machine learning inference on microcontrollers with kilobytes of memory and megahertz processors, two to three orders of magnitude more constrained than conventional edge devices. These extreme limitations render traditional security measures impractical, yet the security implications remain underexplored. Our systematic literature review reveals that fewer than 5% of TinyML publications address security concerns, with even fewer focusing on TinyML-specific vulnerabilities, a critical gap as these devices proliferate in safety-critical applications including healthcare monitoring, autonomous systems, and industrial control. This paper provides a comprehensive security survey specifically addressing TinyML’s resource constraints and unique threat landscape. We develop a resource-based device taxonomy distinguishing IoT, EdgeML, and TinyML security capabilities; formulate a TinyML-specific threat model identifying physical and remote attack vectors; systematically analyze eleven attack classes across hardware, software, and model layers; and assess threat severity using the Common Vulnerability Scoring System (CVSS). For each attack, we evaluate whether conventional countermeasures are feasible under TinyML constraints by assessing computational overhead, memory requirements, and practical deployability on representative platforms. Our analysis reveals critical gaps where existing defenses impose prohibitive overhead, requiring new lightweight solutions. We conclude by identifying open research challenges specific to securing resource-constrained machine learning systems, providing a roadmap for future work.

14 May 2025
Verified
Conference Paper
Open access
JMJames Mickens
James Mickens
SRSarah Radway
Sarah Radway
RNRavi Netravali
Ravi Netravali

23 February 2026 in IEEE Micro
Verified
Journal Article
Closed access
JHJacob Huckelberry
Jacob Huckelberry
AGAndrea Mattia Garavagno
Andrea Mattia Garavagno
YZYuke Zhang
Yuke Zhang
PBPeter Anthony Beerel
Peter Anthony Beerel
JMJames Mickens
James Mickens
VRVijay Janapa Reddi
Vijay Janapa Reddi
Most TinyML hardware focus on supporting Quantized Neural Networks (QNNs) to meet stringent constraints on power consumption, size, and cost. Despite this, the security aspects of quantization within TinyML hardware remain largely unexplored. Although previous studies indicate that QNNs demonstrate similar or enhanced robustness when compared to full-precision Deep Neural Networks (DNNs) against typical evasion attacks, no attack strategies tailored specifically for TinyML hardware have been proposed yet. This paper addresses the aforementioned shortfall by demonstrating how a two-step attack pipeline can surpass the current state-of-the-art in the QNN context and shows the need for more hardware-aware security research.

15 November 2023
Verified
Conference Paper
Open access
XHXueyuan Han
Xueyuan Han
JMJames Mickens
James Mickens
SSSiddhartha Sen
Siddhartha Sen
Splice is a new programming framework that allows security-conscious applications to efficiently locate and delete a user's in-memory state. The core technical challenge is determining how to delete a user's memory values without breaking application-specific semantic invariants involving the memory state of remaining users. Splice solves this problem using three techniques: taint tracking (which traces how a user's data flows through memory), deletion by synthesis (which overwrites each user-owned memory value in place, replacing it with a value that preserves the symbolic constraints of enclosing data structures), and a novel type system (which forces applications to employ defensive programming to avoid computing over synthesize-deleted values in unsafe ways). Using four realistic applications that we ported to Splice, we show that Splice's type system and defensive programming requirements are not onerous for developers. We also demonstrate that Splice's run-time overheads are similar to those of prior taint tracking systems, while enabling strong deletion semantics.