Author name cluster

Tie Luo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

AAAI Conference 2024 Conference Paper

CR-SAM: Curvature Regularized Sharpness-Aware Minimization

Tao Wu
Tie Luo
Donald C. Wunsch II

The capacity to generalize to future unseen data stands as one of the utmost crucial attributes of deep neural networks. Sharpness-Aware Minimization (SAM) aims to enhance the generalizability by minimizing worst-case loss using one-step gradient ascent as an approximation. However, as training progresses, the non-linearity of the loss landscape increases, rendering one-step gradient ascent less effective. On the other hand, multi-step gradient ascent will incur higher training cost. In this paper, we introduce a normalized Hessian trace to accurately measure the curvature of loss landscape on both training and test sets. In particular, to counter excessive non-linearity of loss landscape, we propose Curvature Regularized SAM (CR-SAM), integrating the normalized Hessian trace as a SAM regularizer. Additionally, we present an efficient way to compute the trace via finite differences with parallelism. Our theoretical analysis based on PAC-Bayes bounds establishes the regularizer's efficacy in reducing generalization error. Empirical evaluation on CIFAR and ImageNet datasets shows that CR-SAM consistently enhances classification performance for ResNet and Vision Transformer (ViT) models across various datasets. Our code is available at https://github.com/TrustAIoT/CR-SAM.

PDF Details DOI

AAAI Conference 2024 Conference Paper

LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate

Tao Wu
Tie Luo
Donald C. Wunsch II

The transferability of adversarial examples is of central importance to transfer-based black-box adversarial attacks. Previous works for generating transferable adversarial examples focus on attacking given pretrained surrogate models while the connections between surrogate models and adversarial trasferability have been overlooked. In this paper, we propose Lipschitz Regularized Surrogate (LRS) for transfer-based black-box attacks, a novel approach that transforms surrogate models towards favorable adversarial transferability. Using such transformed surrogate models, any existing transfer-based black-box attack can run without any change, yet achieving much better performance. Specifically, we impose Lipschitz regularization on the loss landscape of surrogate models to enable a smoother and more controlled optimization process for generating more transferable adversarial examples. In addition, this paper also sheds light on the connection between the inner properties of surrogate models and adversarial transferability, where three factors are identified: smaller local Lipschitz constant, smoother loss landscape, and stronger adversarial robustness. We evaluate our proposed LRS approach by attacking state-of-the-art standard deep neural networks and defense models. The results demonstrate significant improvement on the attack success rates and transferability. Our code is available at https://github.com/TrustAIoT/LRS.

PDF Details DOI

AAMAS Conference 2021 Conference Paper

A Blockchain-Enabled Quantitative Approach to Trust and Reputation Management with Sparse Evidence

Leonit Zeynalvand
Tie Luo
Ewa Andrejczuk
Dusit Niyato
Sin G. Teo
Jie Zhang

The prevalence of e-commerce applications poses new trust challenges that render traditional Trust and Reputation Management (TRM) approaches inadequate. The first challenge is that TRM is built on evidence (direct or indirect observations) but evidence is becoming increasingly sparse because nowadays users have many more venues to share information. This makes it hard to derive trust models that are robust to attacks such as whitewashing and Sybil attacks. Second, the cost of attacks has reduced significantly due to the widespread presence of bots in e-commerce applications, which tends to invalidate the traditional assumption that majority users are honest. In this paper, we propose a new TRM framework called BEQA, which uses Blockchain to transform multiple disjoint and sparse sets of evidence into a single and dense evidence set. To address the second challenge, we introduce and formulate the cost of Sybil attacks using Blockchain transaction fees. In addition, we make a key observation that existing trust models have overlooked publicity (evidence originating from influencers) that exist in e-commerce applications. Thus, we formulate publicity as a whitewashing deposit such that a higher level of publicity will impose higher cost on Sybil attacks.

PDF

AAAI Conference 2020 Conference Paper

COBRA: Context-Aware Bernoulli Neural Networks for Reputation Assessment

Leonit Zeynalvand
Tie Luo
Jie Zhang

Trust and reputation management (TRM) plays an increasingly important role in large-scale online environments such as multi-agent systems (MAS) and the Internet of Things (IoT). One main objective of TRM is to achieve accurate trust assessment of entities such as agents or IoT service providers. However, this encounters an accuracy-privacy dilemma as we identify in this paper, and we propose a framework called Context-aware Bernoulli Neural Network based Reputation Assessment (COBRA) to address this challenge. COBRA encapsulates agent interactions or transactions, which are prone to privacy leak, in machine learning models, and aggregates multiple such models using a Bernoulli neural network to predict a trust score for an agent. COBRA preserves agent privacy and retains interaction contexts via the machine learning models, and achieves more accurate trust prediction than a fully-connected neural network alternative. COBRA is also robust to security attacks by agents who inject fake machine learning models; notably, it is resistant to the 51-percent attack. The performance of COBRA is validated by our experiments using a real dataset, and by our simulations, where we also show that COBRA outperforms other state-of-the-art TRM systems.

PDF Details

TCS Journal 2020 Journal Article

Hardness of and approximate mechanism design for the bike rebalancing problem

Hongtao Lv
Fan Wu
Tie Luo
Xiaofeng Gao
Guihai Chen

Recently arose in the flourishing sharing economy, the bike rebalancing problem is a new challenge that concerns how to incentivize users to park bikes at system-desired locations that better meet bike demands. It can also be generalized to other location-based vehicle or tool sharing problems such as car, truck, drone, and trolley sharing. In this paper, we address this problem using an auction model under a crowdsourcing framework, where users report their original destinations and the bike sharing platform assigns proper relocation tasks to them in order to better balance the bike supply and demand. We first prove two impossibility results: (1) finding an optimal solution to the bike rebalancing problem is NP-hard, and (2) there is no approximate mechanism with bounded approximation ratio that is both truthful and budget-feasible. To overcome this barrier, we introduce two practical constraints and design a two-stage approximate mechanism that satisfies location truthfulness, budget feasibility, individual rationality, and achieves constant approximation ratio. To the best of our knowledge, we are the first to address two dimensional location truthfulness in the regime of mechanism design. In addition, our extensive experiments based on real-world dataset demonstrate that our proposed mechanism can effectively redress the imbalance of bike distribution.

Details DOI

AAAI Conference 2020 Conference Paper

Mechanism Design with Predicted Task Revenue for Bike Sharing Systems

Hongtao Lv
Chaoli Zhang
Zhenzhe Zheng
Tie Luo
Fan Wu
Guihai Chen

Bike sharing systems have been widely deployed around the world in recent years. A core problem in such systems is to reposition the bikes so that the distribution of bike supply is reshaped to better match the dynamic bike demand. When the bike-sharing company or platform is able to predict the revenue of each reposition task based on historic data, an additional constraint is to cap the payment for each task below its predicted revenue. In this paper, we propose an incentive mechanism called TruPreTar to incentivize users to park bicycles at locations desired by the platform toward rebalancing supply and demand. TruPreTar possesses four important economic and computational properties such as truthfulness and budget feasibility. Furthermore, we prove that even when the payment budget is tight, the total revenue still exceeds or equals the budget. Otherwise, TruPre- Tar achieves 2-approximation as compared to the optimal (revenue-maximizing) solution, which is close to the lower bound of at least √ 2 that we also prove. Using an industrial dataset obtained from a large bike-sharing company, our experiments show that TruPreTar is effective in rebalancing bike supply and demand and, as a result, generates high revenue that outperforms several benchmark mechanisms.

PDF Details

TIST Journal 2016 Journal Article

Incentive Mechanism Design for Crowdsourcing

Tie Luo
Sajal K. Das
Hwee Pink Tan
Lirong Xia

Crowdsourcing can be modeled as a principal-agent problem in which the principal (crowdsourcer) desires to solicit a maximal contribution from a group of agents (participants) while agents are only motivated to act according to their own respective advantages. To reconcile this tension, we propose an all-pay auction approach to incentivize agents to act in the principal’s interest, i.e., maximizing profit, while allowing agents to reap strictly positive utility. Our rationale for advocating all-pay auctions is based on two merits that we identify, namely all-pay auctions (i) compress the common, two-stage “bid-contribute” crowdsourcing process into a single “bid-cum-contribute” stage, and (ii) eliminate the risk of task nonfulfillment. In our proposed approach, we enhance all-pay auctions with two additional features: an adaptive prize and a general crowdsourcing environment. The prize or reward adapts itself as per a function of the unknown winning agent’s contribution, and the environment or setting generally accommodates incomplete and asymmetric information, risk-averse (and risk-neutral) agents, and a stochastic (and deterministic) population. We analytically derive this all-pay auction-based mechanism and extensively evaluate it in comparison to classic and optimized mechanisms. The results demonstrate that our proposed approach remarkably outperforms its counterparts in terms of the principal’s profit, agent’s utility, and social welfare.

Details DOI