arXiv subjects

Mingyan Liu

Publications and source records attributed to Mingyan Liu.

At least 55 records · Page 3Linked to original sources

arXiv2020

Fairness in Learning-Based Sequential Decision Algorithms: A Survey

Algorithmic fairness in decision-making has been studied extensively in static settings where one-shot decisions are made on tasks such as classification. However, in practice most decision-making processes are of a sequential nature, where decisions made in the past may have an impact on future data. This is particularly the case when decisions affect the individuals or users generating the data used for future decisions. In this survey, we review existing literature on the fairness of data-driven sequential decision-making. We will focus on two types of sequential decisions: (1) past decisions have no impact on the underlying user population and thus no impact on future data; (2) past decisions have an impact on the underlying user population and therefore the future data, which can then impact future decisions. In each case the impact of various fairness interventions on the underlying population is examined.

cs.AI↗

arXiv2019

Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness

Machine Learning (ML) models trained on data from multiple demographic groups can inherit representation disparity (Hashimoto et al., 2018) that may exist in the data: the model may be less favorable to groups contributing less to the training process; this in turn can degrade population retention in these groups over time, and exacerbate representation disparity in the long run. In this study, we seek to understand the interplay between ML decisions and the underlying group representation, how they evolve in a sequential framework, and how the use of fairness criteria plays a role in this process. We show that the representation disparity can easily worsen over time under a natural user dynamics (arrival and departure) model when decisions are made based on a commonly used objective and fairness criteria, resulting in some groups diminishing entirely from the sample pool in the long run. It highlights the fact that fairness criteria have to be defined while taking into consideration the impact of decisions on user dynamics. Toward this end, we explain how a proper fairness criterion can be selected based on a general user dynamics model.

cs.LG↗

arXiv2019

Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms

Alternating direction method of multiplier (ADMM) is a powerful method to solve decentralized convex optimization problems. In distributed settings, each node performs computation with its local data and the local results are exchanged among neighboring nodes in an iterative fashion. During this iterative process the leakage of data privacy arises and can accumulate significantly over many iterations, making it difficult to balance the privacy-accuracy tradeoff. We propose Recycled ADMM (R-ADMM), where a linear approximation is applied to every even iteration, its solution directly calculated using only results from the previous, odd iteration. It turns out that under such a scheme, half of the updates incur no privacy loss and require much less computation compared to the conventional ADMM. Moreover, R-ADMM can be further modified (MR-ADMM) such that each node independently determines its own penalty parameter over iterations. We obtain a sufficient condition for the convergence of both algorithms and provide the privacy analysis based on objective perturbation. It can be shown that the privacy-accuracy tradeoff can be improved significantly compared with conventional ADMM.

cs.LG↗

arXiv2019

Adversarial Objects Against LiDAR-Based Autonomous Driving Systems

Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that adversarial examples can pose a threat to real-world security-critical applications: a "physical adversarial Stop Sign" can be synthesized such that the autonomous driving cars will misrecognize it as others (e.g., a speed limit sign). However, these image-space adversarial examples cannot easily alter 3D scans of widely equipped LiDAR or radar on autonomous vehicles. In this paper, we reveal the potential vulnerabilities of LiDAR-based autonomous driving detection systems, by proposing an optimization based approach LiDAR-Adv to generate adversarial objects that can evade the LiDAR-based detection system under various conditions. We first show the vulnerabilities using a blackbox evolution-based algorithm, and then explore how much a strong adversary can do, using our gradient-based approach LiDAR-Adv. We test the generated adversarial objects on the Baidu Apollo autonomous driving platform and show that such physical systems are indeed vulnerable to the proposed attacks. We also 3D-print our adversarial objects and perform physical experiments to illustrate that such vulnerability exists in the real world. Please find more visualizations and results on the anonymous website: https://sites.google.com/view/lidar-adv.

cs.CR↗

arXiv2019

MeshAdv: Adversarial Meshes for Visual Recognition

Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislead the predictions. Currently, the majority of these studies have focused on perturbation added to image pixels, while such manipulation is not physically realistic. Some works have tried to overcome this limitation by attaching printable 2D patches or painting patterns onto surfaces, but can be potentially defended because 3D shape features are intact. In this paper, we propose meshAdv to generate "adversarial 3D meshes" from objects that have rich shape features but minimal textural variation. To manipulate the shape or texture of the objects, we make use of a differentiable renderer to compute accurate shading on the shape and propagate the gradient. Extensive experiments show that the generated 3D meshes are effective in attacking both classifiers and object detectors. We evaluate the attack under different viewpoints. In addition, we design a pipeline to perform black-box attack on a photorealistic renderer with unknown rendering parameters.

cs.CR↗

arXiv2019

Generating Adversarial Examples with Adversarial Networks

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different attack strategies have been proposed to generate adversarial examples, but how to produce them with high perceptual quality and more efficiently requires more research efforts. In this paper, we propose AdvGAN to generate adversarial examples with generative adversarial networks (GANs), which can learn and approximate the distribution of original instances. For AdvGAN, once the generator is trained, it can generate adversarial perturbations efficiently for any instance, so as to potentially accelerate adversarial training as defenses. We apply AdvGAN in both semi-whitebox and black-box attack settings. In semi-whitebox attacks, there is no need to access the original target model after the generator is trained, in contrast to traditional white-box attacks. In black-box attacks, we dynamically train a distilled model for the black-box model and optimize the generator accordingly. Adversarial examples generated by AdvGAN on different target models have high attack success rate under state-of-the-art defenses compared to other attacks. Our attack has placed the first with 92.76% accuracy on a public MNIST black-box attack challenge.

cs.CR↗

arXiv2018

Distributed Learning of Average Belief Over Networks Using Sequential Observations

This paper addresses the problem of distributed learning of average belief with sequential observations, in which a network of $n>1$ agents aim to reach a consensus on the average value of their beliefs, by exchanging information only with their neighbors. Each agent has sequentially arriving samples of its belief in an online manner. The neighbor relationships among the $n$ agents are described by a graph which is possibly time-varying, whose vertices correspond to agents and whose edges depict neighbor relationships. Two distributed online algorithms are introduced for undirected and directed graphs, which are both shown to converge to the average belief almost surely. Moreover, the sequences generated by both algorithms are shown to reach consensus with an $O(1/t)$ rate with high probability, where $t$ is the number of iterations. For undirected graphs, the corresponding algorithm is modified for the case with quantized communication and limited precision of the division operation. It is shown that the modified algorithm causes all $n$ agents to either reach a quantized consensus or enter a small neighborhood around the average of their beliefs. Numerical simulations are then provided to corroborate the theoretical results.

cs.MA↗

arXiv2018

Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation

Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are well studied in classification tasks, other learning problems may have different properties. For instance, semantic segmentation requires additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in semantic segmentation. We observe that spatial consistency information can be potentially leveraged to detect adversarial examples robustly even when a strong adaptive attacker has access to the model and detection strategies. We also show that adversarial examples based on attacks considered within the paper barely transfer among models, even though transferability is common in classification. Our observations shed new light on developing adversarial attacks and defenses to better understand the vulnerabilities of DNNs.

cs.CR↗

arXiv2018

Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms

Alternating direction method of multiplier (ADMM) is a powerful method to solve decentralized convex optimization problems. In distributed settings, each node performs computation with its local data and the local results are exchanged among neighboring nodes in an iterative fashion. During this iterative process the leakage of data privacy arises and can accumulate significantly over many iterations, making it difficult to balance the privacy-utility tradeoff. In this study we propose Recycled ADMM (R-ADMM), where a linear approximation is applied to every even iteration, its solution directly calculated using only results from the previous, odd iteration. It turns out that under such a scheme, half of the updates incur no privacy loss and require much less computation compared to the conventional ADMM. We obtain a sufficient condition for the convergence of R-ADMM and provide the privacy analysis based on objective perturbation.

cs.CR↗

arXiv2018

Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms

Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy arises. A differentially private ADMM was proposed in prior work (Zhang & Zhu, 2017) where only the privacy loss of a single node during one iteration was bounded, a method that makes it difficult to balance the tradeoff between the utility attained through distributed computation and privacy guarantees when considering the total privacy loss of all nodes over the entire iterative process. We propose a perturbation method for ADMM where the perturbed term is correlated with the penalty parameters; this is shown to improve the utility and privacy simultaneously. The method is based on a modified ADMM where each node independently determines its own penalty parameter in every iteration and decouples it from the dual updating step size. The condition for convergence of the modified ADMM and the lower bound on the convergence rate are also derived.

cs.LG↗

arXiv2018

Spatially Transformed Adversarial Examples

Recent studies show that widely used deep neural networks (DNNs) are vulnerable to carefully crafted adversarial examples. Many advanced algorithms have been proposed to generate adversarial examples by leveraging the $\mathcal{L}_p$ distance for penalizing perturbations. Researchers have explored different defense methods to defend against such adversarial attacks. While the effectiveness of $\mathcal{L}_p$ distance as a metric of perceptual quality remains an active research area, in this paper we will instead focus on a different type of perturbation, namely spatial transformation, as opposed to manipulating the pixel values directly as in prior works. Perturbations generated through spatial transformation could result in large $\mathcal{L}_p$ distance measures, but our extensive experiments show that such spatially transformed adversarial examples are perceptually realistic and more difficult to defend against with existing defense systems. This potentially provides a new direction in adversarial example generation and the design of corresponding defenses. We visualize the spatial transformation based perturbation for different examples and show that our technique can produce realistic adversarial examples with smooth image deformation. Finally, we visualize the attention of deep networks with different types of adversarial examples to better understand how these examples are interpreted.

cs.CR↗

arXiv2017

A Reputation-Based Contract for Repeated Crowdsensing with Costly Verification

We study a setup in which a system operator hires a sensor to exert costly effort to collect accurate measurements of a value of interest over time. At each time, the sensor is asked to report his observation to the operator, and is compensated based on the accuracy of this observation. Since both the effort and observation are private information for the sensor, a naive payment scheme which compensates the sensor based only on his self-reported values will lead to both shirking and falsification of outcomes by the sensor. We consider the problem of designing an appropriate compensation scheme to incentivize the sensor to at once exert costly effort and truthfully reveal the resulting observation. To this end, we formulate the problem as a repeated game and propose a compensation scheme that employs stochastic verification by the operator coupled with a system of assigning reputation to the sensor. In particular, our proposed payment scheme compensates the sensor based on both the effort in the current period as well as the history of past behavior. We show that by using past behavior in determining present payments, the operator can both incentivize higher effort as well as more frequent truthtelling by the sensor and decrease the required verification frequency.

math.OC↗

arXiv2016

Provision of Public Goods on Networks: On Existence, Uniqueness, and Centralities

We consider the provision of public goods on networks of strategic agents. We study different effort outcomes of these network games, namely, the Nash equilibria, Pareto efficient effort profiles, and semi-cooperative equilibria (effort profiles resulting from interactions among coalitions of agents). We identify necessary and sufficient conditions on the structure of the network for the uniqueness of the Nash equilibrium. We show that our finding unifies (and strengthens) existing results in the literature. We also identify conditions for the existence of Nash equilibria for the subclasses of games at the two extremes of our model, namely games of strategic complements and games of strategic substitutes. We provide a graph-theoretical interpretation of agents' efforts at the Nash equilibrium, as well as the Pareto efficient outcomes and semi-cooperative equilibria, by linking an agent's decision to her centrality in the interaction network. Using this connection, we separate the effects of incoming and outgoing edges on agents' efforts and uncover an alternating effect over walks of different length in the network.

cs.GT↗

arXiv2015

An Online Approach to Dynamic Channel Access and Transmission Scheduling

Making judicious channel access and transmission scheduling decisions is essential for improving performance as well as energy and spectral efficiency in multichannel wireless systems. This problem has been a subject of extensive study in the past decade, and the resulting dynamic and opportunistic channel access schemes can bring potentially significant improvement over traditional schemes. However, a common and severe limitation of these dynamic schemes is that they almost always require some form of a priori knowledge of the channel statistics. A natural remedy is a learning framework, which has also been extensively studied in the same context, but a typical learning algorithm in this literature seeks only the best static policy, with performance measured by weak regret, rather than learning a good dynamic channel access policy. There is thus a clear disconnect between what an optimal channel access policy can achieve with known channel statistics that actively exploits temporal, spatial and spectral diversity, and what a typical existing learning algorithm aims for, which is the static use of a single channel devoid of diversity gain. In this paper we bridge this gap by designing learning algorithms that track known optimal or sub-optimal dynamic channel access and transmission scheduling policies, thereby yielding performance measured by a form of strong regret, the accumulated difference between the reward returned by an optimal solution when a priori information is available and that by our online algorithm. We do so in the context of two specific algorithms that appeared in [1] and [2], respectively, the former for a multiuser single-channel setting and the latter for a single-user multichannel setting. In both cases we show that our algorithms achieve sub-linear regret uniform in time and outperforms the standard weak-regret learning algorithms.

cs.LG↗

arXiv2015

A Tale of Two Mechanisms: Incentivizing Investments in Security Games

In a system of interdependent users, the security of an entity is affected not only by that user's investment in security measures, but also by the positive externality of the security decisions of (some of) the other users. The provision of security in such system is therefore modeled as a public good provision problem, and is referred to as a security game. In this paper, we compare two well-known incentive mechanisms in this context for incentivizing optimal security investments among users, namely the Pivotal and the Externality mechanisms. The taxes in a Pivotal mechanism are designed to ensure users' voluntary participation, while those in an Externality mechanism are devised to maintain a balanced budget. We first show the more general result that, due to the non-excludable nature of security, no mechanism can incentivize the socially optimal investment profile, while at the same time ensuring voluntary participation and maintaining a balanced budget for all instances of security games. To further illustrate, we apply the Pivotal and Externality mechanisms to the special case of weighted total effort interdependence models, and identify some of the effects of varying interdependency between users on the budget deficit in the Pivotal mechanism, as well as on the participation incentives in the Externality mechanism.

cs.GT↗

arXiv2015

Optimal Relay Selection with Non-negligible Probing Time

In this paper an optimal relay selection algorithm with non-negligible probing time is proposed and analyzed for cooperative wireless networks. Relay selection has been introduced to solve the degraded bandwidth efficiency problem in cooperative communication. Yet complete information of relay channels often remain unavailable for complex networks which renders the optimal selection strategies impossible for transmission source without probing the relay channels. Particularly when the number of relay candidate is large, even though probing all relay channels guarantees the finding of the best relays at any time instant, the degradation of bandwidth efficiency due to non-negligible probing times, which was often neglected in past literature, is also significant. In this work, a stopping rule based relay selection strategy is determined for the source node to decide when to stop the probing process and choose one of the probed relays to cooperate with under wireless channels' stochastic uncertainties. This relay selection strategy is further shown to have a simple threshold structure. At the meantime, full diversity order and high bandwidth efficiency can be achieved simultaneously. Both analytical and simulation results are provided to verify the claims.

cs.IT↗

arXiv2015

Optimal Adaptive Learning in Uncontrolled Restless Bandit Problems

In this paper we consider the problem of learning the optimal policy for uncontrolled restless bandit problems. In an uncontrolled restless bandit problem, there is a finite set of arms, each of which when pulled yields a positive reward. There is a player who sequentially selects one of the arms at each time step. The goal of the player is to maximize its undiscounted reward over a time horizon T. The reward process of each arm is a finite state Markov chain, whose transition probabilities are unknown by the player. State transitions of each arm is independent of the selection of the player. We propose a learning algorithm with logarithmic regret uniformly over time with respect to the optimal finite horizon policy. Our results extend the optimal adaptive learning of MDPs to POMDPs.

math.OC↗

arXiv2015

Efficient Sensor Fault Detection Using Group Testing

When faulty sensors are rare in a network, diagnosing sensors individually is inefficient. This study introduces a novel use of concepts from group testing and Kalman filtering in detecting these rare faulty sensors with significantly fewer number of tests. By assigning sensors to groups and performing Kalman filter-based fault detection over these groups, we obtain binary detection outcomes, which can then be used to recover the fault state of all sensors. We first present this method using combinatorial group testing. We then present a novel adaptive group testing method based on Bayesian inference. This adaptive method further reduces the number of required tests and is suitable for noisy group test systems. Compared to non-group testing methods, our algorithm achieves similar detection accuracy with fewer tests and thus lower computational complexity. Compared to other adaptive group testing methods, the proposed method achieves higher accuracy when test results are noisy. We perform extensive numerical analysis using a set of real vibration data collected from the New Carquinez Bridge in California using an 18-sensor network mounted on the bridge. We also discuss how the features of the Kalman filter-based group test can be exploited in forming groups and further improving the detection accuracy.

eess.SY↗