Dimitrios I. Diochnos

Dimitrios I. Diochnos

Auto-generated profile, based on publicly available information

Dimitrios I. Diochnos

University of Oklahoma

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
17 July 2019 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
SMSaeed Mahloujifar
Saeed Mahloujifar
DDDimitrios I. Diochnos
Dimitrios I. Diochnos
MMMohammad Mahmoody
Mohammad Mahmoody
Many modern machine learning classifiers are shown to be vulnerable to adversarial perturbations of the instances. Despite a massive amount of work focusing on making classifiers robust, the task seems quite challenging. In this work, through a theoretical study, we investigate the adversarial risk and robustness of classifiers and draw a connection to the well-known phenomenon of “concentration of measure” in metric measure spaces. We show that if the metric probability space of the test instance is concentrated, any classifier with some initial constant error is inherently vulnerable to adversarial perturbations.One class of concentrated metric probability spaces are the so-called Lévy families that include many natural distributions. In this special case, our attacks only need to perturb the test instance by at most O(√n) to make it misclassified, where n is the data dimension. Using our general result about Lévy instance spaces, we first recover as special case some of the previously proved results about the existence of adversarial examples. However, many more Lévy families are known (e.g., product distribution under the Hamming distance) for which we immediately obtain new attacks that find adversarial examples of distance O(√n).Finally, we show that concentration of measure for product spaces implies the existence of forms of “poisoning” attacks in which the adversary tampers with the training data with the goal of degrading the classifier. In particular, we show that for any learning algorithm that uses m training examples, there is an adversary who can increase the probability of any “bad property” (e.g., failing on a particular test instance) that initially happens with non-negligible probability to ≈ 1 by substituting only Õe(√m) of the examples with other (still correctly labeled) examples.

1 July 2009 in Journal of Symbolic Computation
Verified
Journal Article
Closed access
DDDimitrios I. Diochnos
Dimitrios I. Diochnos
IEIoannis Z. Emiris
Ioannis Z. Emiris
ETElias P. Tsigaridas
Elias P. Tsigaridas

29 July 2007
Verified
Conference Paper
Open access
PDF file
DDDimitrios I. Diochnos
Dimitrios I. Diochnos
IEIoannis Z. Emiris
Ioannis Z. Emiris
ETElias P. Tsigaridas
Elias P. Tsigaridas
We consider exact real solving of well-constrained, bivariate systems of relatively prime polynomials. The main problem is to compute all common real roots in isolating interval representation, and to determine their intersection multiplicities. We present three algorithms and analyze their asymptotic bit complexity, obtaining a bound of ÕB(N14) for the purely projection-based method, and ÕB(N12) for two subresultants-based methods: these ignore polylogarithmic factors, and N bounds the degree and the bitsize of the polynomials. The previous record bound was ÕB(N14). Our main tool is signed subresultant sequences, extended to several variables by binary segmentation. We exploit advances on the complexity of univariate root isolation, and extend them to multipoint sign evaluation, sign evaluation of bivariate polynomials over two algebraic numbers, and real root counting over an extension field. Our algorithms apply to the problem of simultaneous inequalities; they also compute the topology of real plane algebraic curves in. All algorithms have been implemented in maple, in conjunction with numeric filtering. We compare them against fgb/rs and synaps; we also consider maple libraries insulate and top, which compute curve topology. Our software is among the most robust, and its runtimes are within a small constant factor, with respect to the C/C++ libraries.

17 March 2026 in Journal of Artificial Intelligence Research
Verified
Journal Article
Closed access
PDF file
PKPatrick Kage
Patrick Kage
JRJay Rothenberger
Jay Rothenberger
PAPavlos Andreadis
Pavlos Andreadis
DDDimitrios Diochnos
Dimitrios Diochnos
Deep neural models have achieved state-of-the-art performance on a wide range of problems in computer science, especially in computer vision. However, deep neural networks often require large datasets of labeled samples to generalize effectively. An important area of active research is semi-supervised learning, which attempts to instead utilize large quantities of (easily acquired) unlabeled samples. One family of methods in this space is pseudo-labeling, a class of algorithms that use model outputs to assign labels to unlabeled samples which are then used as labeled samples during training. Such assigned labels, called pseudo-labels, are most commonly associated with the field of semi-supervised learning. In this work, we explore a broader interpretation of pseudo-labels within both self-supervised and unsupervised methods. After a thorough treatment of pseudo-labeling in these areas, we draw the connection between them and identify commonalities between fields, as well as new directions where advancements in one area would likely benefit others, such as curriculum learning and self-supervised regularization.

1 October 2015
Verified
Conference Paper
Closed access
OSOgnjen Scekic
Ognjen Scekic
DMDaniele Miorandi
Daniele Miorandi
TSTommaso Schiavinotto
Tommaso Schiavinotto
DDDimitrios I. Diochnos
Dimitrios I. Diochnos
AHAlethia Hume
Alethia Hume
FGFausto Giunchiglia
Fausto Giunchiglia
Society is moving towards a socio-technical ecosystem in which physical and virtual dimensions of life are intertwined and where people interactions ever more take place with or are mediated by machines. Hybrid Diversity-aware Collective Adaptive Systems (HDA-CAS) is a new generation of socio-technical systems where humans and machines synergetically complement each other and operate collectively to achieve their goals. HDA-CAS introduce the fundamental properties of hybridity and collectiveness, hiding from the users the complexities associated with managing the collaboration and coordination of machine and human computing elements. In this paper we present an HDA-CAS system called Smart Society, supporting computations with hybrid human/machine collectives. We describe the platform's architecture and functionality, validate it on two real-world scenarios involving human and machine elements and present a performance evaluation.