arXiv subjects

Yevgeniy Vorobeychik

Publications and source records attributed to Yevgeniy Vorobeychik.

158 records · Page 9Linked to original sources

arXiv2017

Optimal Thresholds for Anomaly-Based Intrusion Detection in Dynamical Environments

In cyber-physical systems, malicious and resourceful attackers could penetrate the system through cyber means and cause significant physical damage. Consequently, detection of such attacks becomes integral towards making these systems resilient to attacks. To achieve this objective, intrusion detection systems (IDS) that are able to detect malicious behavior can be deployed. However, practical IDS are imperfect and sometimes they may produce false alarms for a normal system behavior. Since alarms need to be investigated for any potential damage, a large number of false alarms may increase the operational costs significantly. Thus, IDS need to be configured properly, as oversensitive IDS could detect attacks early but at the cost of a higher number of false alarms. Similarly, IDS with low sensitivity could reduce the false alarms while increasing the time to detect the attacks. The configuration of IDS to strike the right balance between time to detecting attacks and the rate of false positives is a challenging task, especially in dynamic environments, in which the damage incurred by a successful attack is time-varying. In this paper, we study the problem of finding optimal detection thresholds for anomaly-based detectors implemented in dynamical systems in the face of strategic attacks. We formulate the problem as an attacker-defender security game, and determine thresholds for the detector to achieve an optimal trade-off between the detection delay and the false positive rates. In this direction, first, we provide an algorithm that computes optimal fixed threshold that remains fixed throughout. Second, we allow detector's threshold to change with time to further minimize the defender's loss and provide an algorithm to compute time-varying thresholds, which we call adaptive thresholds. Finally, we numerically evaluate our results using a water distribution network as a case-study.

cs.GT↗

arXiv2016

A General Retraining Framework for Scalable Adversarial Classification

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom methods have been developed for both adversarial evasion attacks and robust learning. We propose the first systematic and general-purpose retraining framework which can: a) boost robustness of an \emph{arbitrary} learning algorithm, in the face of b) a broader class of adversarial models than any prior methods. We show that, under natural conditions, the retraining framework minimizes an upper bound on optimal adversarial risk, and show how to extend this result to account for approximations of evasion attacks. Extensive experimental evaluation demonstrates that our retraining methods are nearly indistinguishable from state-of-the-art algorithms for optimizing adversarial risk, but are more general and far more scalable. The experiments also confirm that without retraining, our adversarial framework dramatically reduces the effectiveness of learning. In contrast, retraining significantly boosts robustness to evasion attacks without significantly compromising overall accuracy.

cs.GT↗

arXiv2016

Data Poisoning Attacks on Factorization-Based Collaborative Filtering

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in the industry, their outputs could affect business decision making, introducing incentives for an adversarial party to compromise the availability or integrity of such systems. We introduce a data poisoning attack on collaborative filtering systems. We demonstrate how a powerful attacker with full knowledge of the learner can generate malicious data so as to maximize his/her malicious objectives, while at the same time mimicking normal user behavior to avoid being detected. While the complete knowledge assumption seems extreme, it enables a robust assessment of the vulnerability of collaborative filtering schemes to highly motivated attacks. We present efficient solutions for two popular factorization-based collaborative filtering algorithms: the \emph{alternative minimization} formulation and the \emph{nuclear norm minimization} method. Finally, we test the effectiveness of our proposed algorithms on real-world data and discuss potential defensive strategies.

cs.LG↗

arXiv2016

Scheduling Resource-Bounded Monitoring Devices for Event Detection and Isolation in Networks

In networked systems, monitoring devices such as sensors are typically deployed to monitor various target locations. Targets are the points in the physical space at which events of some interest, such as random faults or attacks, can occur. Most often, these devices have limited energy supplies, and they can operate for a limited duration. As a result, energy-efficient monitoring of various target locations through a set of monitoring devices with limited energy supplies is a crucial problem in networked systems. In this paper, we study optimal scheduling of monitoring devices to maximize network coverage for detecting and isolating events on targets for a given network lifetime. The monitoring devices considered could remain active only for a fraction of the overall network lifetime. We formulate the problem of scheduling of monitoring devices as a graph labeling problem, which unlike other existing solutions, allows us to directly utilize the underlying network structure to explore the trade-off between coverage and network lifetime. In this direction, first we propose a greedy heuristic to solve the graph labeling problem, and then provide a game-theoretic solution to achieve near optimal graph labeling. Moreover, the proposed setup can be used to simultaneously solve the scheduling and placement of monitoring devices, which yields improved performance as compared to separately solving the placement and scheduling problems. Finally, we illustrate our results on various networks, including real-world water distribution networks.

cs.NI↗

arXiv2016

Robust High-Dimensional Linear Regression

The effectiveness of supervised learning techniques has made them ubiquitous in research and practice. In high-dimensional settings, supervised learning commonly relies on dimensionality reduction to improve performance and identify the most important factors in predicting outcomes. However, the economic importance of learning has made it a natural target for adversarial manipulation of training data, which we term poisoning attacks. Prior approaches to dealing with robust supervised learning rely on strong assumptions about the nature of the feature matrix, such as feature independence and sub-Gaussian noise with low variance. We propose an integrated method for robust regression that relaxes these assumptions, assuming only that the feature matrix can be well approximated by a low-rank matrix. Our techniques integrate improved robust low-rank matrix approximation and robust principle component regression, and yield strong performance guarantees. Moreover, we experimentally show that our methods significantly outperform state of the art both in running time and prediction error.

cs.LG↗

arXiv2016

Predicting Human Cooperation

The Prisoner's Dilemma has been a subject of extensive research due to its importance in understanding the ever-present tension between individual self-interest and social benefit. A strictly dominant strategy in a Prisoner's Dilemma (defection), when played by both players, is mutually harmful. Repetition of the Prisoner's Dilemma can give rise to cooperation as an equilibrium, but defection is as well, and this ambiguity is difficult to resolve. The numerous behavioral experiments investigating the Prisoner's Dilemma highlight that players often cooperate, but the level of cooperation varies significantly with the specifics of the experimental predicament. We present the first computational model of human behavior in repeated Prisoner's Dilemma games that unifies the diversity of experimental observations in a systematic and quantitatively reliable manner. Our model relies on data we integrated from many experiments, comprising 168,386 individual decisions. The computational model is composed of two pieces: the first predicts the first-period action using solely the structural game parameters, while the second predicts dynamic actions using both game parameters and history of play. Our model is extremely successful not merely at fitting the data, but in predicting behavior at multiple scales in experimental designs not used for calibration, using only information about the game structure. We demonstrate the power of our approach through a simulation analysis revealing how to best promote human cooperation.

cs.GT↗

arXiv2015

Multidefender Security Games

Stackelberg security game models and associated computational tools have seen deployment in a number of high-consequence security settings, such as LAX canine patrols and Federal Air Marshal Service. These models focus on isolated systems with only one defender, despite being part of a more complex system with multiple players. Furthermore, many real systems such as transportation networks and the power grid exhibit interdependencies between targets and, consequently, between decision makers jointly charged with protecting them. To understand such multidefender strategic interactions present in security, we investigate game theoretic models of security games with multiple defenders. Unlike most prior analysis, we focus on the situations in which each defender must protect multiple targets, so that even a single defender's best response decision is, in general, highly non-trivial. We start with an analytical investigation of multidefender security games with independent targets, offering an equilibrium and price-of-anarchy analysis of three models with increasing generality. In all models, we find that defenders have the incentive to over-protect targets, at times significantly. Additionally, in the simpler models, we find that the price of anarchy is unbounded, linearly increasing both in the number of defenders and the number of targets per defender. Considering interdependencies among targets, we develop a novel mixed-integer linear programming formulation to compute a defender's best response, and make use of this formulation in approximating Nash equilibria of the game. We apply this approach towards computational strategic analysis of several models of networks representing interdependencies, including real-world power networks. Our analysis shows how network structure and the probability of failure spread determine the propensity of defenders to over- or under-invest in security.

cs.GT↗

arXiv2015

Mechanism Design for Team Formation

Team formation is a core problem in AI. Remarkably, little prior work has addressed the problem of mechanism design for team formation, accounting for the need to elicit agents' preferences over potential teammates. Coalition formation in the related hedonic games has received much attention, but only from the perspective of coalition stability, with little emphasis on the mechanism design objectives of true preference elicitation, social welfare, and equity. We present the first formal mechanism design framework for team formation, building on recent combinatorial matching market design literature. We exhibit four mechanisms for this problem, two novel, two simple extensions of known mechanisms from other domains. Two of these (one new, one known) have desirable theoretical properties. However, we use extensive experiments to show our second novel mechanism, despite having no theoretical guarantees, empirically achieves good incentive compatibility, welfare, and fairness.

cs.GT↗

arXiv2014

Characterizing short-term stability for Boolean networks over any distribution of transfer functions

We present a characterization of short-term stability of random Boolean networks under \emph{arbitrary} distributions of transfer functions. Given any distribution of transfer functions for a random Boolean network, we present a formula that decides whether short-term chaos (damage spreading) will happen. We provide a formal proof for this formula, and empirically show that its predictions are accurate. Previous work only works for special cases of balanced families. It has been observed that these characterizations fail for unbalanced families, yet such families are widespread in real biological networks.

nlin.CD↗

arXiv2012

Computing Optimal Security Strategies for Interdependent Assets

We introduce a novel framework for computing optimal randomized security policies in networked domains which extends previous approaches in several ways. First, we extend previous linear programming techniques for Stackelberg security games to incorporate benefits and costs of arbitrary security configurations on individual assets. Second, we offer a principled model of failure cascades that allows us to capture both the direct and indirect value of assets, and extend this model to capture uncertainty about the structure of the interdependency network. Third, we extend the linear programming formulation to account for exogenous (random) failures in addition to targeted attacks. The goal of our work is two-fold. First, we aim to develop techniques for computing optimal security strategies in realistic settings involving interdependent security. To this end, we evaluate the value of our technical contributions in comparison with previous approaches, and show that our approach yields much better defense policies and scales to realistic graphs. Second, our computational framework enables us to attain theoretical insights about security on networks. As an example, we study how allowing security to be endogenous impacts the relative resilience of different network topologies.

cs.GT↗

arXiv2012

Constrained Automated Mechanism Design for Infinite Games of Incomplete Information

We present a functional framework for automated mechanism design based on a two-stage game model of strategic interaction between the designer and the mechanism participants, and apply it to several classes of two-player infinite games of incomplete information. At the core of our framework is a black-box optimization algorithm which guides the selection process of candidate mechanisms. Our approach yields optimal or nearly optimal mechanisms in several application domains using various objective functions. By comparing our results with known optimal mechanisms, and in some cases improving on the best known mechanisms, we provide evidence that ours is a promising approach to parametric design of indirect mechanisms.

cs.GT↗

arXiv2012

Simulation-Based Game Theoretic Analysis of Keyword Auctions with Low-Dimensional Bidding Strategies

We perform a simulation-based analysis of keyword auctions modeled as one-shot games of incomplete information to study a series of mechanism design questions. Our first question addresses the degree to which incentive compatibility fails in generalized second-price (GSP) auctions. Our results suggest that sincere bidding in GSP auctions is a strikingly poor strategy and a poor predictor of equilibrium outcomes. We next show that the rank-by-revenue mechanism is welfare optimal, corroborating past results. Finally, we analyze profit as a function of auction mechanism under a series of alternative settings. Our conclusions coincide with those of Lahaie and Pennock [2007] when values and quality scores are strongly positively correlated: in such a case, rank-by-bid rules are clearly superior. We diverge, however, in showing that auctions that put little weight on quality scores almost universally dominate the pure rank-by-revenue scheme.

cs.GT↗

arXiv2011

Influence and Dynamic Behavior in Random Boolean Networks

We present a rigorous mathematical framework for analyzing dynamics of a broad class of Boolean network models. We use this framework to provide the first formal proof of many of the standard critical transition results in Boolean network analysis, and offer analogous characterizations for novel classes of random Boolean networks. We precisely connect the short-run dynamic behavior of a Boolean network to the average influence of the transfer functions. We show that some of the assumptions traditionally made in the more common mean-field analysis of Boolean networks do not hold in general. For example, we offer some evidence that imbalance, or expected internal inhomogeneity, of transfer functions is a crucial feature that tends to drive quiescent behavior far more strongly than previously observed.

cond-mat.dis-nn↗

arXiv2011

Noncooperatively Optimized Tolerance: Decentralized Strategic Optimization in Complex Systems

We introduce noncooperatively optimized tolerance (NOT), a generalization of highly optimized tolerance (HOT) that involves strategic (game theoretic) interactions between parties in a complex system. We illustrate our model in the forest fire (percolation) framework. As the number of players increases, our model retains features of HOT, such as robustness, high yield combined with high density, and self-dissimilar landscapes, but also develops features of self-organized criticality (SOC) when the number of players is large enough. For example, the forest landscape becomes increasingly homogeneous and protection from adverse events (lightning strikes) becomes less closely correlated with the spatial distribution of these events. While HOT is a special case of our model, the resemblance to SOC is only partial; for example, the distribution of cascades, while becoming increasingly heavy-tailed as the number of players increases, also deviates more significantly from a power law in this regime. Surprisingly, the system retains considerable robustness even as it becomes fractured, due in part to emergent cooperation between neighboring players. At the same time, increasing homogeneity promotes resilience against changes in the lightning distribution, giving rise to intermediate regimes where the system is robust to a particular distribution of adverse events, yet not very fragile to changes.

cs.GT↗