An official website of the United States government
Emerging technologies drive the ongoing transformation of Intelligent Transportation Systems (ITS). This transformation has given rise to cybersecurity concerns, among which data poisoning attack emerges as a new threat as ITS increasingly relies on data. In data poisoning attacks, attackers inject malicious perturbations into datasets, potentially leading to inaccurate results in offline learning and real-time decision-making processes. This paper concentrates on data poisoning attack models against ITS. We identify the main ITS data sources vulnerable to poisoning attacks and application scenarios that enable staging such attacks. A general framework is developed following rigorous study process from cybersecurity but also considering specific ITS application needs. Data poisoning attacks against ITS are reviewed and categorized following the framework. We then discuss the current limitations of these attack models and the future research directions. Our work can serve as a guideline to better understand the threat of data poisoning attacks against ITS applications, while also giving a perspective on the future development of trustworthy ITS. Emerging technologies drive the ongoing transformation of Intelligent Transportation Systems (ITS). This transformation has given rise to cybersecurity concerns, among which data poisoning attack emerges as a new threat as ITS increasingly relies on data. In data poisoning attacks, attackers inject malicious perturbations into datasets, potentially leading to inaccurate results in offline learning and real-time decision-making processes. This paper concentrates on data poisoning attack models against ITS. We identify the main ITS data sources vulnerable to poisoning attacks and application scenarios that enable staging such attacks. A general framework is developed following rigorous study process from cybersecurity but also considering specific ITS application needs. Data poisoning attacks against ITS are reviewed and categorized following the framework. We then discuss the current limitations of these attack models and the future research directions. Our work can serve as a guideline to better understand the threat of data poisoning attacks against ITS applications, while also giving a perspective on the future development of trustworthy ITS.
more »
« less
Get A Head Start: On‑demand Pedagogical Policy Selection in Intelligent Tutoring
Proposes EduPlanner, an ODPS pipeline that selects personalized pedagogical policies via subgroup identification over historical and live ITS data. Evaluated in a long-running Probability ITS, EDUPlanner improves learning outcomes, particularly for low-performing subgroups.
more »
« less
- Award ID(s):
- 2013502
- PAR ID:
- 10609446
- Publisher / Repository:
- Proceedings of the Thirty‑eighth AAAI Conference on Artificial Intelligence / AAAI Press
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
As the largest-bodied member of the family Lemuridae and the presumed primary disperser of large seeds, Pachylemur, now extinct, was a critical member of Madagascar’s primate communities. Material of this genus has been found at almost all subfossil sites across Madagascar, but extensive samples of this taxon are known from very few. It has been one of the more historically neglected of the “giant” extinct lemurs, as it is not very different in morphology from its nearest extant relative, Varecia, except in body size. The flooded cave called Vintany at the Tsimanampesotse National Park in southwestern Madagascar has yielded numerous specimens of P. insignis, including whole skulls and mandibles, many isolated postcranial elements, and, importantly, partial associated skeletons of immature individuals. This material allows us to address previously unanswered questions regarding its paleobiology, including questions concerning its growth and development. This article focuses specifically on its life history profile (especially developmental sequences and life history-related traits such as Retzius line periodicity of the teeth and endocranial volume in adults). We ask to what extent, despite its larger size, did Pachylemur “grow” like its smaller-bodied relatives? Did its dental eruption sequence and index of Relative Retardation of the Replacement teeth resemble those of its closest relatives? Did it, like other lemurs, have a Retzius line periodicity that is lower than “expected” for a primate of its body size, and if so, what is the likely significance of this? Was its brain smaller than expected for a primate of its body size? For these and other questions, we evaluate how large-bodied lemurs differ from anthropoids of comparable body size.more » « less
-
Context. Asteroid (22) Kalliope is the second largest M-type asteroid in the main belt and is orbited by a satellite, Linus. Whereas the mass of Kalliope is already well constrained thanks to the presence of a moon, its volume is still poorly known, leading to uncertainties on its bulk density and internal structure. Aims. We aim to refine the shape of (22) Kalliope and thus its diameter and bulk density, as well as the orbit of its moon to better constrain its mass, hence density and internal structure. Methods. We acquired disk-resolved observations of (22) Kalliope using the VLT/SPHERE/ZIMPOL instrument to reconstruct its three-dimensional (3D) shape using three different modeling techniques. These images were also used together with new speckle observations at the C2PU/PISCO instrument as well as archival images from other large ground-based telescopes to refine the orbit of Linus. Results. The volume of (22) Kalliope given by the shape models, corresponding to D = 150 ± 5 km, and the mass constrained by its satellite’s orbit yield a density of ρ = 4.40 ± 0.46 g cm −3 . This high density potentially makes (22) Kalliope the densest known small body in the Solar System. A macroporosity in the 10–25% range (as expected for this mass and size), implies a grain density in the 4.8–5.9 g cm −3 range. Kalliope’s high bulk density, along with its silicate-rich surface implied by its low radar albedo, implies a differentiated interior with metal contributing to most of the mass of the body. Conclusions. Kalliope’s high metal content (40–60%) along with its metal-poor mantle makes it the smallest known Mercury-like body. A large impact at the origin of the formation of the moon Linus is likely the cause of its high metal content and density.more » « less
-
Abstract Since the discovery of the Higgs boson in 2012, detailed studies of its properties have been ongoing. Besides its mass, its width—related to its lifetime—is an important parameter. One way to determine this quantity is to measure its off-shell production, where the Higgs boson mass is far away from its nominal value, and relating it to its on-shell production, where the mass is close to the nominal value. Here we report evidence for such off-shell contributions to the production cross-section of two Z bosons with data from the CMS experiment at the CERN Large Hadron Collider. We constrain the total rate of the off-shell Higgs boson contribution beyond the Z boson pair production threshold, relative to its standard model expectation, to the interval [0.0061, 2.0] at the 95% confidence level. The scenario with no off-shell contribution is excluded at a p -value of 0.0003 (3.6 standard deviations). We measure the width of the Higgs boson as $${{{\varGamma }}}_{{{{{{\rm{H}}}}}}}={3.2}_{-1.7}^{+2.4}\,{{{{{\rm{MeV}}}}}}$$ Γ H = 3.2 − 1.7 + 2.4 MeV , in agreement with the standard model expectation of 4.1 MeV. In addition, we set constraints on anomalous Higgs boson couplings to W and Z boson pairs.more » « less
-
A "quine" is a deterministic program that prints itself. In this essay, I will show you a "gauguine": a probabilistic program that infers itself. A gauguine is repeatedly asked to guess its own source code. Initially, its chances of guessing correctly are of course minuscule. But as the gauguine observes more and more of its own previous guesses, it detects patterns of behavior and gains information about its inner workings. This information allows it to bootstrap self-knowledge, and ultimately discover its own source code. We will discuss how—and why—we might write a gauguine, and what we stand to learn by constructing one.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Proceeding:
- The DOI is not currently available.
