Publications

Refine Results

(Filters Applied) Clear All

Poisoning network flow classifiers [e-print]

June 2, 2023
  |
Journal Article
Author:
Giorgio Severi
…
Published in:
arXiv:2306.01655v1 [cs.CR]
Topic:
networking
R&D area:
R&D group:

Summary

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor attacks, against network traffic flow classifiers. We investigate the challenging scenario of clean-label poisoning where the adversary's capabilities are constrained to tampering only with the training data - without the ability to arbitrarily modify the training labels or any other component of the training process. We describe a trigger crafting strategy that leverages model interpretability techniques to generate trigger patterns that are effective even at very low poisoning rates. Finally, we design novel strategies to generate stealthy triggers, including an approach based on generative Bayesian network models, with the goal of minimizing the conspicuousness of the trigger, and thus making detection of an ongoing poisoning campaign more challenging. Our findings provide significant insights into the feasibility of poisoning attacks on network traffic classifiers used in multiple scenarios, including detecting malicious communication and application classification.
READ LESS

Summary

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor attacks, against network traffic flow classifiers. We investigate the challenging scenario of clean-label poisoning where the adversary's capabilities are constrained to...

READ MORE
Poisoning network flow classifiers [e-print]

Improving long-text authorship verification via model selection and data tuning

May 5, 2023
  |
Conference Paper
Author:
Trang D. Nguyen
…
Published in:
Proc. 7th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, LaTeCH-CLfL2023, 5 May 2023, pp. 28-37.
Topic:
machine learning
R&D area:
R&D group:

Summary

Authorship verification is used to link texts written by the same author without needing a model per author, making it useful for deanonymizing users spreading text with malicious intent. Recent advances in Transformer-based language models hold great promise for author verification, though short context lengths and non-diverse training regimes present challenges for their practical application. In this work, we investigate the effect of these challenges in the application of a Cross-Encoder Transformer-based author verification system under multiple conditions. We perform experiments with four Transformer backbones using differently tuned variants of fanfiction data and found that our BigBird pipeline outperformed Longformer, RoBERTa, and ELECTRA and performed competitively against the official top ranked system from the PAN evaluation. We also examined the effect of authors and fandoms not seen in training on model performance. Through this, we found fandom has the greatest influence on true trials, pairs of text written by the same author, and that a balanced training dataset in terms of class and fandom performed the most consistently.
READ LESS

Summary

Authorship verification is used to link texts written by the same author without needing a model per author, making it useful for deanonymizing users spreading text with malicious intent. Recent advances in Transformer-based language models hold great promise for author verification, though short context lengths and non-diverse training regimes present...

READ MORE
Improving long-text authorship verification via model selection and data tuning

Holding the high ground: Defending satellites from cyber attack

March 31, 2023
  |
Journal Article
Author:
Richard W. Skowyra
…
Published in:
The Cyber Edge by Signal, 31 March 2023.
Topic:
cyber security
R&D area:
R&D group:

Summary

MIT Lincoln Laboratory and the Space Cyber-Resiliency group at Air Force Research Laboratory-Space Vehicles Directorate have prototyped a practical, operationally capable and secure-by-design spaceflight software platform called Cyber-Hardened Satellite Software (CHSS) for building space mission applications with security, recoverability and performance as first-class system design priorities. Following a successful evaluation of CHSS against an existing U.S. Space Force (USSF) mission, the CHSS platform is currently being extended to support hybrid space vehicle architectures that incorporate both CHSS-aware and legacy subsystems. CHSS has the potential to revolutionize the cyber-resiliency of space systems and substantially ease the burden of defensive cyber operations (DCO).
READ LESS

Summary

MIT Lincoln Laboratory and the Space Cyber-Resiliency group at Air Force Research Laboratory-Space Vehicles Directorate have prototyped a practical, operationally capable and secure-by-design spaceflight software platform called Cyber-Hardened Satellite Software (CHSS) for building space mission applications with security, recoverability and performance as first-class system design priorities. Following a successful evaluation...

READ MORE
Holding the high ground: Defending satellites from cyber attack

Network performance of pLEO topologies in a high-inclination Walker Delta Satellite Constellation

March 4, 2023
  |
Conference Paper
Author:
Thomas H. Shake
…
Published in:
IEEE Aerospace Conf. Proc., 4-11 March 2023, 188722.
Topic:
satellites
R&D area:
R&D group:

Summary

Low-earth-orbit satellite constellations with hundreds to thousands of satellites are emerging as practical alternatives for providing various types of data services such as global networking and large-scale sensing. The network performance of these satellite constellations is strongly dependent on the topology of the inter-satellite links (ISLs) in such systems. This paper studies the effects of six different ISL topologies, coupled with three configurations of ground relay terminals, on path failure rate, path latency, and link transmission efficiency in an example highly-inclined Walker Delta constellation with 360 satellites. These network performance parameters are calculated in the presence of satellite failures in the constellation. Trade-offs between ISL connection density and overall performance are examined and quantified. Topologies with 4 active ISLs per satellite are shown to perform significantly better than topologies requiring fewer, especially as the average number of active ISLs per satellite becomes significantly less than three. Latencies for a topology requiring 3 active ISLs per satellite are shown to be between 15 and 60% higher than for a 4-ISL reference topology. Path availabilities for the 3-ISL topology are shown to be on the order of 30% lower for a benchmark case of 10 satellite failures. The performance of near-minimal topologies (e.g., an average of 2.2 active ISLs per satellite) is much worse. Latency reductions of 10-30% and path failure rate improvements on the order of 45% are shown to be obtainable by the inclusion of 2 to 5 strategically located ground relay stations
READ LESS

Summary

Low-earth-orbit satellite constellations with hundreds to thousands of satellites are emerging as practical alternatives for providing various types of data services such as global networking and large-scale sensing. The network performance of these satellite constellations is strongly dependent on the topology of the inter-satellite links (ISLs) in such systems. This...

READ MORE
Network performance of pLEO topologies in a high-inclination Walker Delta Satellite Constellation

Development of 3D-Printed Individualized Vascular Phantoms for Artificial Intelligence (AI) Enabled Interventional Device Testing

March 1, 2023
  |
Abstract
Author:
Theodore T. Pierce
…
Published in:
Journal of Vascular and Interventional Radiology 34 (3), S12.
Topic:
3D printing
R&D area:
R&D group:

Summary

We developed vascular phantoms mapped from human subjects to test AI-enabled ultrasound-guided vascular cannulation. Translational device prototyping necessitates anatomically accurate models. Commercial phantoms fail to address anatomic variability. Uniformity leads to optimistic AI model and operator performance. Individualized 3D-printed vascular phantoms yield anatomically correct models optimized for AI-device testing.
READ LESS

Summary

We developed vascular phantoms mapped from human subjects to test AI-enabled ultrasound-guided vascular cannulation. Translational device prototyping necessitates anatomically accurate models. Commercial phantoms fail to address anatomic variability. Uniformity leads to optimistic AI model and operator performance. Individualized 3D-printed vascular phantoms yield anatomically correct models optimized for AI-device testing.

READ MORE
Development of 3D-Printed Individualized Vascular Phantoms for Artificial Intelligence (AI) Enabled Interventional Device Testing

Automated exposure notification for COVID-19

February 14, 2023
  |
Technical Report
Author:
Ronald L. Rivest
…
Published in:
MIT Lincoln Laboratory Report TR-1288
Topic:
health
R&D area:
R&D group:

Summary

Private Automated Contact Tracing (PACT) was a collaborative team and effort formed during the beginning of the Coronavirus Disease 2019 (COVID-19) pandemic. PACT's mission was to enhance contact tracing in pandemic response by designing exposure-detection functions in personal digital communication devices that have maximal public health utility while preserving privacy. This report explains and discusses the use of automated exposure notification during the COVID-19 pandemic and to provide some recommendations for those who may try to design and deploy similar technologies in future pandemics.
READ LESS

Summary

Private Automated Contact Tracing (PACT) was a collaborative team and effort formed during the beginning of the Coronavirus Disease 2019 (COVID-19) pandemic. PACT's mission was to enhance contact tracing in pandemic response by designing exposure-detection functions in personal digital communication devices that have maximal public health utility while preserving privacy...

READ MORE
Automated exposure notification for COVID-19

A generative approach to condition-aware score calibration for speaker verification

February 8, 2023
  |
Journal Article
Author:
Bengt J. Borgstrom
Published in:
IEEE/ACM Trans. Audio, Speech, Language Process., Vol. 31, 2023, pp. 891-901.
Topic:
speech processing
R&D area:
R&D group:

Summary

In speaker verification, score calibration is employed to transform verification scores to log-likelihood ratios (LLRs) which are statistically interpretable. Conventional calibration techniques apply a global score transform. However, in condition-aware (CA) calibration, information conveying signal conditions is provided as input, allowing calibration to be adaptive. This paper explores a generative approach to condition-aware score calibration. It proposes a novel generative model for speaker verification trials, each which includes a trial score, a trial label, and the associated pair of speaker embeddings. Trials are assumed to be drawn from a discrete set of underlying signal conditions which are modeled as latent Categorical random variables, so that trial scores and speaker embeddings are drawn from condition-dependent distributions. An Expectation-Maximization (EM) Algorithm for parameter estimation of the proposed model is presented, which does not require condition labels and instead discovers relevant conditions in an unsupervised manner. The generative condition-aware (GCA) calibration transform is then derived as the log-likelihood ratio of a verification score given the observed pair of embeddings. Experimental results show the proposed approach to provide performance improvements on a variety of speaker verification tasks, outperforming static and condition-aware baseline calibration methods. GCA calibration is observed to improve the discriminative ability of the speaker verification system, as well as provide good calibration performance across a range of operating points. The benefits of the proposed method are observed for task-dependent models where signal conditions are known, for universal models which are robust across a range of conditions, and when facing unseen signal conditions.
READ LESS

Summary

In speaker verification, score calibration is employed to transform verification scores to log-likelihood ratios (LLRs) which are statistically interpretable. Conventional calibration techniques apply a global score transform. However, in condition-aware (CA) calibration, information conveying signal conditions is provided as input, allowing calibration to be adaptive. This paper explores a generative...

READ MORE
A generative approach to condition-aware score calibration for speaker verification

Dissociating COVID-19 from other respiratory infections based on acoustic, motor coordination, and phonemic patterns

January 28, 2023
  |
Journal Article
Author:
Tanya Talkar
…
Published in:
Sci. Rep., Vol. 13, No. 1, January 2023, 1567.
Topic:
speech
R&D area:
R&D group:

Summary

In the face of the global pandemic caused by the disease COVID-19, researchers have increasingly turned to simple measures to detect and monitor the presence of the disease in individuals at home. We sought to determine if measures of neuromotor coordination, derived from acoustic time series, as well as phoneme-based and standard acoustic features extracted from recordings of simple speech tasks could aid in detecting the presence of COVID-19. We further hypothesized that these features would aid in characterizing the effect of COVID-19 on speech production systems. A protocol, consisting of a variety of speech tasks, was administered to 12 individuals with COVID-19 and 15 individuals with other viral infections at University Hospital Galway. From these recordings, we extracted a set of acoustic time series representative of speech production subsystems, as well as their univariate statistics. The time series were further utilized to derive correlation-based features, a proxy for speech production motor coordination. We additionally extracted phoneme-based features. These features were used to create machine learning models to distinguish between the COVID-19 positive and other viral infection groups, with respiratory- and laryngeal-based features resulting in the highest performance. Coordination-based features derived from harmonic-to-noise ratio time series from read speech discriminated between the two groups with an area under the ROC curve (AUC) of 0.94. A longitudinal case study of two subjects, one from each group, revealed differences in laryngeal based acoustic features, consistent with observed physiological differences between the two groups. The results from this analysis highlight the promise of using nonintrusive sensing through simple speech recordings for early warning and tracking of COVID-19.
READ LESS

Summary

In the face of the global pandemic caused by the disease COVID-19, researchers have increasingly turned to simple measures to detect and monitor the presence of the disease in individuals at home. We sought to determine if measures of neuromotor coordination, derived from acoustic time series, as well as phoneme-based...

READ MORE
Dissociating COVID-19 from other respiratory infections based on acoustic, motor coordination, and phonemic patterns

An emotion-driven vocal biomarker-based PTSD screening tool

January 1, 2023
  |
Journal Article
Author:
Thomas F. Quatieri
…
Published in:
IEEE Open J. Eng. Med. Biol., early access, 2023.
Topic:
health
R&D area:
R&D group:

Summary

This paper introduces an automated post-traumatic stress disorder (PTSD) screening tool that could potentially be used as a self-assessment or inserted into routine medical visits for PTSD diagnosis and treatment. Methods: With an emotion estimation algorithm providing arousal (excited to calm) and valence (pleasure to displeasure) levels through discourse, we select regions of the acoustic signal that are most salient for PTSD detection. Our algorithm was tested on a subset of data from the DVBIC-TBICoE TBI Study, which contains PTSD Check List Civilian (PCL-C) assessment scores. Results: Speech from low-arousal and positive-valence regions provide the best discrimination for PTSD. Our model achieved an AUC (area under the curve) equal to 0.80 in detecting PCL-C ratings, outperforming models with no emotion filtering (AUC = 0.68). Conclusions: This result suggests that emotion drives the selection of the most salient temporal regions of an audio recording for PTSD detection.
READ LESS

Summary

This paper introduces an automated post-traumatic stress disorder (PTSD) screening tool that could potentially be used as a self-assessment or inserted into routine medical visits for PTSD diagnosis and treatment. Methods: With an emotion estimation algorithm providing arousal (excited to calm) and valence (pleasure to displeasure) levels through discourse, we...

READ MORE
An emotion-driven vocal biomarker-based PTSD screening tool

Noninvasive monitoring of simulated hemorrhage and whole blood resuscitation

December 14, 2022
  |
Journal Article
Author:
Jay Gupta
…
Published in:
Biosensors, Vol. 12, No. 12, 2022, Art. No. 1168.
Topic:
biomedical
R&D area:
R&D group:

Summary

Hemorrhage is the leading cause of preventable death from trauma. Accurate monitoring of hemorrhage and resuscitation can significantly reduce mortality and morbidity but remains a challenge due to the low sensitivity of traditional vital signs in detecting blood loss and possible hemorrhagic shock. Vital signs are not reliable early indicators because of physiological mechanisms that compensate for blood loss and thus do not provide an accurate assessment of volume status. As an alternative, machine learning (ML) algorithms that operate on an arterial blood pressure (ABP) waveform have been shown to provide an effective early indicator. However, these ML approaches lack physiological interpretability. In this paper, we evaluate and compare the performance of ML models trained on nine ABP-derived features that provide physiological insight, using a database of 13 human subjects from a lower-body negative pressure (LBNP) model of progressive central hypovolemia and subsequent progressive restoration to normovolemia (i.e., simulated hemorrhage and whole blood resuscitation). Data were acquired at multiple repressurization rates for each subject to simulate varying resuscitation rates, resulting in 52 total LBNP collections. This work is the first to use a single ABP-based algorithm to monitor both simulated hemorrhage and resuscitation. A gradient-boosted regression tree model trained on only the half-rise to dicrotic notch (HRDN) feature achieved a root-mean-square error (RMSE) of 13%, an R2 of 0.82, and area under the receiver operating characteristic curve of 0.97 for detecting decompensation. This single-feature model's performance compares favorably to previously reported results from more-complex black box machine learning models. This model further provides physiological insight because HRDN represents an approximate measure of the delay between the ABP ejected and reflected wave and therefore is an indication of cardiac and peripheral vascular mechanisms that contribute to the compensatory response to blood loss and replacement.
READ LESS

Summary

Hemorrhage is the leading cause of preventable death from trauma. Accurate monitoring of hemorrhage and resuscitation can significantly reduce mortality and morbidity but remains a challenge due to the low sensitivity of traditional vital signs in detecting blood loss and possible hemorrhagic shock. Vital signs are not reliable early indicators...

READ MORE
Noninvasive monitoring of simulated hemorrhage and whole blood resuscitation
41-50 of 2318