Author name cluster

Pengpeng Chen

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.

6 papers

1 author row

AAAI Conference 2026 Short Paper

Misclassification-Aware Robust Learning from Multiple Human Labelers (Student Abstract)

Zuoyuehe Wang
Chicheng Ma
Pengpeng Chen
Lei Chai
Yongqiang Yang
Zhijun Chen
Jingzheng Li
Bing Li

Adversarial training is an effective technique for enhancing the robustness of deep neural networks (DNNs). Prior research shows that misclassified examples influence final adversarial robustness much more than correctly classified examples. Ignoring this difference during training can hurt model performance. In crowdsourcing, varying annotator expertise causes noisy, inconsistent labels. As a result, it is hard to distinguish misclassified and correctly classified examples using only provided annotations. Thus, how to use the reliability and discrepancy between these example types to improve robustness within adversarial learning remains a critical but underexplored issue. In this work, we first explore how misclassified and correctly classified examples affect learning from crowds (LFC) in adversarial environments. Then, we formulate the problem of misclassification-aware robust learning from multiple human labelers as a bilevel min-max problem. After that, we introduce MALC, a new approach to make classifiers more robust to adversarial examples via iterative adversarial example generation and parameter estimation. We conduct an extensive evaluation of the proposed MALC, showing that MALC can outperform the state-of-the-art LFC methods in both white-box and black-box settings.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

Black-Box Data Poisoning Attacks on Crowdsourcing

Pengpeng Chen
Yongqiang Yang
Dingqi Yang
Hailong Sun
Zhijun Chen
Peng Lin

Understanding the vulnerability of label aggregation against data poisoning attacks is key to ensuring data quality in crowdsourced label collection. State-of-the-art attack mechanisms generally assume full knowledge of the aggregation models while failing to consider the flexibility of malicious workers in selecting which instances to label. Such a setup limits the applicability of the attack mechanisms and impedes further improvement of their success rate. This paper introduces a black-box data poisoning attack framework that finds the optimal strategies for instance selection and labeling to attack unknown label aggregation models in crowdsourcing. We formulate the attack problem on top of a generic formalization of label aggregation models and then introduce a substitution approach that attacks a substitute aggregation model in replacement of the unknown model. Through extensive validation on multiple real-world datasets, we demonstrate the effectiveness of both instance selection and model substitution in improving the success rate of attacks.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Adversarial Learning from Crowds

Pengpeng Chen
Hailong Sun
Yongqiang Yang
Zhijun Chen

Learning from Crowds (LFC) seeks to induce a high-quality classifier from training instances, which are linked to a range of possible noisy annotations from crowdsourcing workers under their various levels of skills and their own preconditions. Recent studies on LFC focus on designing new methods to improve the performance of the classifier trained from crowdsourced labeled data. To this day, however, there remain under-explored security aspects of LFC systems. In this work, we seek to bridge this gap. We first show that LFC models are vulnerable to adversarial examples—small changes to input data can cause classifiers to make prediction mistakes. Second, we propose an approach, A-LFC for training a robust classifier from crowdsourced labeled data. Our empirical results on three real-world datasets show that the proposed approach can substantially improve the performance of the trained classifier even with the existence of adversarial examples. On average, A-LFC has 10. 05% and 11. 34% higher test robustness than the state-of-the-art in the white-box and black-box attack settings, respectively.

PDF Details

TCS Journal 2022 Journal Article

Gaussian downlink user selection subject to access limit, power budget, and rate demands

Xiang Liu
Jinyu Zou
Pengpeng Chen
Peng-Jun Wan

Consider a Gaussian downlink between an access point with power budget P > 0, and a set of users specified by their effective noises and rate demands. In order to control the decoding complexity and error propagation, an integer-valued access limit M > 0 is imposed on the number of superimposed users. For each subset S of users, its (total) power demand p ( S ) is a strictly increasing and nonseparable function of the effective noises and rate demands of users in S. A subset S of users is feasible if | S | ≤ M and p ( S ) ≤ P. The goal is to select a feasible subset S of users whose total rate demand is maximized. In this paper, we show that this problem is NP-hard, and present a ( 1 − 1 / e ) -approximation algorithm for this problem. In addition, we also give several other approximation algorithms with trade-offs between accuracy and efficiency.

Details DOI

IJCAI Conference 2020 Conference Paper

Structured Probabilistic End-to-End Learning from Crowds

Zhijun Chen
Huimin Wang
Hailong Sun
Pengpeng Chen
Tao Han
Xudong Liu
Jie Yang

End-to-end learning from crowds has recently been introduced as an EM-free approach to training deep neural networks directly from noisy crowdsourced annotations. It models the relationship between true labels and annotations with a specific type of neural layer, termed as the crowd layer, which can be trained using pure backpropagation. Parameters of the crowd layer, however, can hardly be interpreted as annotator reliability, as compared with the more principled probabilistic approach. The lack of probabilistic interpretation further prevents extensions of the approach to account for important factors of annotation processes, e. g. , instance difficulty. This paper presents SpeeLFC, a structured probabilistic model that incorporates the constraints of probability axioms for parameters of the crowd layer, which allows to explicitly model annotator reliability while benefiting from the end-to-end training of neural networks. Moreover, we propose SpeeLFC-D, which further takes into account instance difficulty. Extensive validation on real-world datasets shows that our methods improve the state-of-the-art.

PDF Details DOI

IJCAI Conference 2018 Conference Paper

On the Cost Complexity of Crowdsourcing

Yili Fang
Hailong Sun
Pengpeng Chen
Jinpeng Huai

Existing efforts mainly use empirical analysis to evaluate the effectiveness of crowdsourcing methods, which is often unreliable across experimental settings. Consequently, it is of great importance to study theoretical methods. This work, for the first time, defines the cost complexity of crowdsourcing, and presents two theorems to compute the cost complexity. Our theorems provide a general theoretical method to model the trade-off between costs and quality, which can be used to evaluate and design crowdsourcing algorithms, and characterize the complexity of crowdsourcing problems. Moreover, following our theorems, we prove a set of corollaries that can obtain existing theoretical results for special cases. We have verified our work theoretically and empirically.

PDF Details