Search Results for author: Yevgeniy Vorobeychik

Found 50 papers, 14 papers with code

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum

1 code implementation21 Jun 2022 Junlin Wu, Yevgeniy Vorobeychik

Despite considerable advances in deep reinforcement learning, it has been shown to be highly vulnerable to adversarial perturbations to state observations.

Adversarial Robustness reinforcement-learning

Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop at AAAI 2022

no code implementations28 Feb 2022 James Holt, Edward Raff, Ahmad Ridley, Dennis Ross, Arunesh Sinha, Diane Staheli, William Streilen, Milind Tambe, Yevgeniy Vorobeychik, Allan Wollaber

These challenges are widely studied in enterprise networks, but there are many gaps in research and practice as well as novel problems in other domains.

Networked Restless Multi-Armed Bandits for Mobile Interventions

no code implementations28 Jan 2022 Han-Ching Ou, Christoph Siebenbrunner, Jackson Killian, Meredith B Brooks, David Kempe, Yevgeniy Vorobeychik, Milind Tambe

Motivated by a broad class of mobile intervention problems, we propose and study restless multi-armed bandits (RMABs) with network effects.

Multi-Armed Bandits

Unfairness Despite Awareness: Group-Fair Classification with Strategic Agents

no code implementations6 Dec 2021 Andrew Estornell, Sanmay Das, Yang Liu, Yevgeniy Vorobeychik

These conditions are related to the the way in which the fair classifier remedies unfairness on the original unmanipulated data: fair classifiers which remedy unfairness by becoming more selective than their conventional counterparts are the ones that become less fair than their counterparts when agents are strategic.

Classification Decision Making +1

PROVES: Establishing Image Provenance using Semantic Signatures

1 code implementation21 Oct 2021 Mingyang Xie, Manav Kulshrestha, Shaojie Wang, Jinghan Yang, Ayan Chakrabarti, Ning Zhang, Yevgeniy Vorobeychik

Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results.

Face Verification

Computing an Optimal Pitching Strategy in a Baseball At-Bat

no code implementations8 Oct 2021 Connor Douglas, Everett Witt, Mia Bendy, Yevgeniy Vorobeychik

Specifically, we propose a novel model of this encounter as a zero-sum stochastic game, in which the goal of the batter is to get on base, an outcome the pitcher aims to prevent.

Learning Generative Deception Strategies in Combinatorial Masking Games

no code implementations23 Sep 2021 Junlin Wu, Charles Kamhoua, Murat Kantarcioglu, Yevgeniy Vorobeychik

Next, we present a novel highly scalable approach for approximately solving such games by representing the strategies of both players as neural networks.

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

2 code implementations ICLR 2022 Fan Wu, Linyi Li, Zijian Huang, Yevgeniy Vorobeychik, Ding Zhao, Bo Li

We then develop a local smoothing algorithm for policies derived from Q-functions to guarantee the robustness of actions taken along the trajectory; we also develop a global smoothing algorithm for certifying the lower bound of a finite-horizon cumulative reward, as well as a novel local smoothing algorithm to perform adaptive search in order to obtain tighter reward certification.

Atari Games Autonomous Vehicles +1

Altruism Design in Networked Public Goods Games

no code implementations2 May 2021 Sixie Yu, David Kempe, Yevgeniy Vorobeychik

Many collective decision-making settings feature a strategic tension between agents acting out of individual self-interest and promoting a common good.

Decision Making

FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems

1 code implementation CVPR 2021 Liang Tong, Zhengzhang Chen, Jingchao Ni, Wei Cheng, Dongjin Song, Haifeng Chen, Yevgeniy Vorobeychik

Moreover, we observe that open-set face recognition systems are more vulnerable than closed-set systems under different types of attacks.

Face Recognition

Re-identification of Individuals in Genomic Datasets Using Public Face Images

1 code implementation17 Feb 2021 Rajagopal Venkatesaramani, Bradley A. Malin, Yevgeniy Vorobeychik

However, recent studies have suggested that genomic data can be effectively matched to high-resolution three-dimensional face images, which raises a concern that the increasingly ubiquitous public face images can be linked to shared genomic data, thereby re-identifying individuals in the genomic data.

Incentivizing Truthfulness Through Audits in Strategic Classification

no code implementations16 Dec 2020 Andrew Estornell, Sanmay Das, Yevgeniy Vorobeychik

While this policy can, in general, be hard to compute because of the difficulty of identifying the set of agents who could benefit from lying given a complete set of reported types, we also present necessary and sufficient conditions under which it is tractable.

Multiagent Systems Computer Science and Game Theory

Finding Physical Adversarial Examples for Autonomous Driving with Fast and Differentiable Image Compositing

1 code implementation17 Oct 2020 Jinghan Yang, Adith Boloor, Ayan Chakrabarti, Xuan Zhang, Yevgeniy Vorobeychik

We propose a scalable approach for finding adversarial modifications of a simulated autonomous driving environment using a differentiable approximation for the mapping from environmental modifications (rectangles on the road) to the corresponding video inputs to the controller neural network.

Autonomous Driving Self-Driving Cars

Optimizing Graph Structure for Targeted Diffusion

1 code implementation12 Aug 2020 Sixie Yu, Leonardo Torres, Scott Alfeld, Tina Eliassi-Rad, Yevgeniy Vorobeychik

However, in many applications, such as targeted vulnerability assessment or clinical therapies, one aspires to affect a targeted subset of a network, while limiting the impact on the rest.

Social and Information Networks Physics and Society

Robust Collective Classification against Structural Attacks

no code implementations26 Jul 2020 Kai Zhou, Yevgeniy Vorobeychik

Finally, we apply our approach in a transductive learning setting, and show that robust AMN is much more robust than state-of-the-art deep learning methods, while sacrificing little in accuracy on non-adversarial data.

Adversarial Robustness Classification +1

Adversarial Robustness of Deep Sensor Fusion Models

no code implementations23 Jun 2020 Shaojie Wang, Tong Wu, Ayan Chakrabarti, Yevgeniy Vorobeychik

First, we find that the fusion model is usually both more accurate, and more robust against single-source attacks than single-sensor deep neural networks.

2D object detection Adversarial Robustness +4

A Review of Incident Prediction, Resource Allocation, and Dispatch Models for Emergency Management

no code implementations7 Jun 2020 Ayan Mukhopadhyay, Geoffrey Pettet, Sayyed Vazirizade, Di Lu, Said El Said, Alex Jaimes, Hiba Baroud, Yevgeniy Vorobeychik, Mykel Kochenderfer, Abhishek Dubey

In the last fifty years, researchers have developed statistical, data-driven, analytical, and algorithmic approaches for designing and improving emergency response management (ERM) systems.

Decision Making Decision Making Under Uncertainty

Towards Robustness against Unsuspicious Adversarial Examples

no code implementations8 May 2020 Liang Tong, Minzhe Guo, Atul Prakash, Yevgeniy Vorobeychik

We then experimentally demonstrate that our attacks indeed do not significantly change perceptual salience of the background, but are highly effective against classifiers robust to conventional attacks.

Inducing Equilibria in Networked Public Goods Games through Network Structure Modification

no code implementations25 Feb 2020 David Kempe, Sixie Yu, Yevgeniy Vorobeychik

Networked public goods games model scenarios in which self-interested agents decide whether or how much to invest in an action that benefits not only themselves, but also their network neighbors.

Computer Science and Game Theory Multiagent Systems

On Algorithmic Decision Procedures in Emergency Response Systems in Smart and Connected Communities

no code implementations21 Jan 2020 Geoffrey Pettet, Ayan Mukhopadhyay, Mykel Kochenderfer, Yevgeniy Vorobeychik, Abhishek Dubey

This is not a trivial planning problem --- a major challenge with dynamically balancing the spatial distribution of responders is the complexity of the problem.

Decision Making Decision Making Under Uncertainty

Protecting Geolocation Privacy of Photo Collections

1 code implementation4 Dec 2019 Jinghan Yang, Ayan Chakrabarti, Yevgeniy Vorobeychik

We study this problem formally as a combinatorial optimization problem in the context of geolocation prediction facilitated by deep learning.

Combinatorial Optimization

Adversarial Deep Reinforcement Learning based Adaptive Moving Target Defense

no code implementations27 Nov 2019 Taha Eghtesad, Yevgeniy Vorobeychik, Aron Laszka

In this paper, we propose a multi-agent partially-observable Markov Decision Process model of MTD and formulate a two-player general-sum game between the adversary and the defender.

Multi-agent Reinforcement Learning reinforcement-learning

Deception through Half-Truths

no code implementations14 Nov 2019 Andrew Estornell, Sanmay Das, Yevgeniy Vorobeychik

Deception is a fundamental issue across a diverse array of settings, from cybersecurity, where decoys (e. g., honeypots) are an important tool, to politics that can feature politically motivated "leaks" and fake news about candidates. Typical considerations of deception view it as providing false information. However, just as important but less frequently studied is a more tacit form where information is strategically hidden or leaked. We consider the problem of how much an adversary can affect a principal's decision by "half-truths", that is, by masking or hiding bits of information, when the principal is oblivious to the presence of the adversary.

Computing Equilibria in Binary Networked Public Goods Games

no code implementations13 Nov 2019 Sixie Yu, Kai Zhou, P. Jeffrey Brantingham, Yevgeniy Vorobeychik

Public goods games study the incentives of individuals to contribute to a public good and their behaviors in equilibria.

Computer Science and Game Theory

A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models

1 code implementation5 Nov 2019 Ren Pang, Hua Shen, Xinyang Zhang, Shouling Ji, Yevgeniy Vorobeychik, Xiapu Luo, Alex Liu, Ting Wang

Specifically, (i) we develop a new attack model that jointly optimizes adversarial inputs and poisoned models; (ii) with both analytical and empirical evidence, we reveal that there exist intriguing "mutual reinforcement" effects between the two attack vectors -- leveraging one vector significantly amplifies the effectiveness of the other; (iii) we demonstrate that such effects enable a large design spectrum for the adversary to enhance the existing attacks that exploit both vectors (e. g., backdoor attacks), such as maximizing the attack evasiveness with respect to various detection methods; (iv) finally, we discuss potential countermeasures against such optimized attacks and their technical challenges, pointing to several promising research directions.

Path Planning Games

no code implementations30 Oct 2019 Yi Li, Yevgeniy Vorobeychik

Path planning is a fundamental and extensively explored problem in robotic control.

Defending Against Physically Realizable Attacks on Image Classification

2 code implementations ICLR 2020 Tong Wu, Liang Tong, Yevgeniy Vorobeychik

Finally, we demonstrate that adversarial training using our new attack yields image classification models that exhibit high robustness against the physically realizable attacks we study, offering the first effective generic defense against such attacks.

Classification General Classification +1

Adversarial Robustness of Similarity-Based Link Prediction

no code implementations3 Sep 2019 Kai Zhou, Tomasz P. Michalak, Yevgeniy Vorobeychik

We propose a novel approach for increasing robustness of similarity-based link prediction by endowing the analyst with a restricted set of reliable queries which accurately measure the existence of queried links.

Adversarial Robustness Link Prediction

Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning

no code implementations20 Jun 2019 Liang Tong, Aron Laszka, Chao Yan, Ning Zhang, Yevgeniy Vorobeychik

We then use these in a double-oracle framework to obtain an approximate equilibrium of the game, which in turn yields a robust stochastic policy for the defender.

Intrusion Detection reinforcement-learning

Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models

no code implementations12 Mar 2019 Adith Boloor, Xin He, Christopher Gill, Yevgeniy Vorobeychik, Xuan Zhang

Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception.

Autonomous Driving

An Online Decision-Theoretic Pipeline for Responder Dispatch

no code implementations21 Feb 2019 Ayan Mukhopadhyay, Geoffrey Pettet, Chinmaya Samal, Abhishek Dubey, Yevgeniy Vorobeychik

We highlight why such an approach is crucial to the effectiveness of emergency response, and present an algorithmic framework that can compute promising actions for a given decision-theoretic model for responder dispatch.

Distributionally Robust Removal of Malicious Nodes from Networks

no code implementations31 Jan 2019 Sixie Yu, Yevgeniy Vorobeychik

An important problem in networked systems is detection and removal of suspected malicious nodes.

Removing Malicious Nodes from Networks

1 code implementation30 Dec 2018 Sixie Yu, Yevgeniy Vorobeychik

In reality, detection is always imperfect, and the decision about which potentially malicious nodes to remove must trade off false positives (erroneously removing benign nodes) and false negatives (mistakenly failing to remove malicious nodes).

Regularized Ensembles and Transferability in Adversarial Learning

no code implementations5 Dec 2018 Yifan Chen, Yevgeniy Vorobeychik

Despite the considerable success of convolutional neural networks in a broad array of domains, recent research has shown these to be vulnerable to small adversarial perturbations, commonly known as adversarial examples.

Attacking Similarity-Based Link Prediction in Social Networks

no code implementations22 Sep 2018 Kai Zhou, Tomasz P. Michalak, Talal Rahwan, Marcin Waniek, Yevgeniy Vorobeychik

We offer a comprehensive algorithmic investigation of the problem of attacking similarity-based link prediction through link deletion, focusing on two broad classes of such approaches, one which uses only local information about target links, and another which uses global network information.

Social and Information Networks Cryptography and Security

Attack Tolerance of Link Prediction Algorithms: How to Hide Your Relations in a Social Network

no code implementations1 Sep 2018 Marcin Waniek, Kai Zhou, Yevgeniy Vorobeychik, Esteban Moro, Tomasz P. Michalak, Talal Rahwan

Link prediction is one of the fundamental research problems in network analysis.

Social and Information Networks Cryptography and Security 91D30 (Primary) 68T20 (Secondary) G.2.2; J.4

Adversarial Regression with Multiple Learners

1 code implementation ICML 2018 Liang Tong, Sixie Yu, Scott Alfeld, Yevgeniy Vorobeychik

We present an algorithm for computing this equilibrium, and show through extensive experiments that equilibrium models are significantly more robust than conventional regularized linear regression.

Optical Neural Networks

no code implementations16 May 2018 Grant Fennessy, Yevgeniy Vorobeychik

We develop a novel optical neural network (ONN) framework which introduces a degree of scalar invariance to image classification estima- tion.

General Classification Image Classification

Community Detection by Information Flow Simulation

1 code implementation13 May 2018 Rajagopal Venkatesaramani, Yevgeniy Vorobeychik

Community detection remains an important problem in data mining, owing to the lack of scalable algorithms that exploit all aspects of available data - namely the directionality of flow of information and the dynamics thereof.

Social and Information Networks Physics and Society

Adversarial Regression for Detecting Attacks in Cyber-Physical Systems

no code implementations30 Apr 2018 Amin Ghafouri, Yevgeniy Vorobeychik, Xenofon Koutsoukos

Attacks in cyber-physical systems (CPS) which manipulate sensor readings can cause enormous physical damage if undetected.

Get Your Workload in Order: Game Theoretic Prioritization of Database Auditing

no code implementations22 Jan 2018 Chao Yan, Bo Li, Yevgeniy Vorobeychik, Aron Laszka, Daniel Fabbri, Bradley Malin

For enhancing the privacy protections of databases, where the increasing amount of detailed personal data is stored and processed, multiple mechanisms have been developed, such as audit logging and alert triggers, which notify administrators about suspicious activities; however, the two main limitations in common are: 1) the volume of such alerts is often substantially greater than the capabilities of resource-constrained organizations, and 2) strategic attackers may disguise their actions or carefully choosing which records they touch, making incompetent the statistical detection models.

Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features

no code implementations28 Aug 2017 Liang Tong, Bo Li, Chen Hajaj, Chaowei Xiao, Ning Zhang, Yevgeniy Vorobeychik

A conventional approach to evaluate ML robustness to such attacks, as well as to design robust ML, is by considering simplified feature-space models of attacks, where the attacker changes ML features directly to effect evasion, while minimizing or constraining the magnitude of this change.

Intrusion Detection Malware Detection

Empirically Grounded Agent-Based Models of Innovation Diffusion: A Critical Review

no code implementations30 Aug 2016 Haifeng Zhang, Yevgeniy Vorobeychik

Innovation diffusion has been studied extensively in a variety of disciplines, including sociology, economics, marketing, ecology, and computer science.

Robust High-Dimensional Linear Regression

no code implementations7 Aug 2016 Chang Liu, Bo Li, Yevgeniy Vorobeychik, Alina Oprea

The effectiveness of supervised learning techniques has made them ubiquitous in research and practice.

Dimensionality Reduction

A General Retraining Framework for Scalable Adversarial Classification

no code implementations9 Apr 2016 Bo Li, Yevgeniy Vorobeychik, Xinyun Chen

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.

Classification General Classification

Multidefender Security Games

no code implementations28 May 2015 Jian Lou, Andrew M. Smith, Yevgeniy Vorobeychik

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.

Feature Cross-Substitution in Adversarial Classification

no code implementations NeurIPS 2014 Bo Li, Yevgeniy Vorobeychik

The success of machine learning, particularly in supervised settings, has led to numerous attempts to apply it in adversarial settings such as spam and malware detection.

Classification feature selection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.