623 Hits in 4.2 sec

An Adversarial Imitation Click Model for Information Retrieval [article]

Xinyi Dai, Jianghao Lin, Weinan Zhang, Shuai Li, Weiwen Liu, Ruiming Tang, Xiuqiang He, Jianye Hao, Jun Wang, Yong Yu
2021 pre-print
In this paper, we propose a novel framework, Adversarial Imitation Click Model (AICM), based on imitation learning.  ...  Click models, which study how users interact with a ranked list of items, provide a useful understanding of user feedback for learning ranking models.  ...  ACKNOWLEDGEMENT We thank Minghuan Liu and Jian Shen for helpful discussions.  ... 
doi:10.1145/3442381.3449913 arXiv:2104.06077v1 fatcat:esyaa7ru3fhg3g5xs2zg4pfdua

Imitate TheWorld: A Search Engine Simulation Platform [article]

Yongqing Gao, Guangda Huzhang, Weijie Shen, Yawen Liu, Wen-Ji Zhou, Qing Da, Yang Yu
2021 arXiv   pre-print
Generative Adversarial Imitation Learning (GAIL) to capture behavior patterns of users.  ...  Towards the issues, we build a simulated search engine AESim that can properly give feedback by a well-trained discriminator for generated pages, as a dynamic dataset.  ...  Our model follows generative adversarial imitation learning (GAIL) [10] , which has been examined to be a better choice for imitation learning [9, 11, 23] , to learn the patterns of real users.  ... 
arXiv:2107.07693v2 fatcat:nmf6sfxl5vftda53mfdeqduqxu


Jun Wang, Lantao Yu, Weinan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, Dell Zhang
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
On the other hand, the generative model, acting as an attacker to the current discriminative model, generates difficult examples for the discriminative model in an adversarial way by minimising its discrimination  ...  This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative  ...  nets (GANs) [13] , thus our IRGAN, opens a door of learning generative and discriminative retrieval models in an adversarial se ing.  ... 
doi:10.1145/3077136.3080786 dblp:conf/sigir/WangYZGXWZZ17 fatcat:l3luiqya4zeunebhwzg6mrxme4

Generative Adversarial User Model for Reinforcement Learning Based Recommendation System [article]

Xinshi Chen, Shuang Li, Hui Li, Shaohua Jiang, Yuan Qi, Le Song
2020 arXiv   pre-print
reward for the user and higher click rate for the system.  ...  In this paper, we propose a novel model-based reinforcement learning framework for recommendation systems, where we develop a generative adversarial network to imitate user behavior dynamics and learn  ...  Generative Adversarial User Model We propose a model to imitate users' sequential choices and discuss its parameterization and estimation.  ... 
arXiv:1812.10613v3 fatcat:ylle2zjuvze7xaqnun5tvwm3w4

Survey on web spam detection

Nikita Spirin, Jiawei Han
2012 SIGKDD Explorations  
Over the last decade research on adversarial information retrieval has gained a lot of interest both from academia and industry.  ...  behaviour, clicks, HTTP sessions.  ...  area of adversarial information retrieval.  ... 
doi:10.1145/2207243.2207252 fatcat:euakka22anfs7cbwatkguk224e

Forensic Verification and Detection of Fake Video using Deep Fake Algorithm

Prachi Kale
2021 International Journal for Research in Applied Science and Engineering Technology  
This gigantic utilization of computerized pictures has been trailed by an increment of methods to change picture substance, utilizing altering programming like Photoshop for instance.  ...  Deepfakes are a sort of video or picture imitation created to spread deception, attack protection, and veil the truth utilizing cutting edge innovations like prepared calculations, profound learning applications  ...  Train Model-This option/button has been hidden for normal users for system safety. By clicking this button a new model can be trained.  ... 
doi:10.22214/ijraset.2021.35599 fatcat:ulqplrlhdba3pi755uhnwoeynm

Designing challenge questions for location‐based authentication systems: a real‐life study

Yusuf Albayram, Mohammad Maifi Hasan Khan, Athanasios Bamis, Sotirios Kentros, Nhan Nguyen, Ruhua Jiang
2015 Human-Centric Computing and Information Sciences  
Online service providers often use challenge questions (a.k.a. knowledge-based authentication) to facilitate resetting of passwords or to provide an extra layer of security for authentication.  ...  and present a Bayesian classifier based authentication algorithm that can authenticate legitimate users with high accuracy by leveraging individual response patterns while reducing the success rate of adversaries  ...  Please note that, due to the use of models, to compromise the authentication scheme, an attacker needs to closely imitate the response behavior of a legitimate user (i.e., having high accuracy does not  ... 
doi:10.1186/s13673-015-0032-3 fatcat:upxj5qlq4jgeflswyvmqaqjx4u

WebGPT: Browser-assisted question-answering with human feedback [article]

Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe (+6 others)
2022 arXiv   pre-print
By setting up the task so that it can be performed by humans, we are able to train models on the task using imitation learning, and then optimize answer quality with human feedback.  ...  Our best model is obtained by fine-tuning GPT-3 using behavior cloning, and then performing rejection sampling against a reward model trained to predict human preferences.  ...  thank Surge AI for helping us with data collection, in particular Edwin Chen, Andrew Mauboussin, Craig Pettit and Bradley Webb.  ... 
arXiv:2112.09332v2 fatcat:qmzgb4x6fnfynhewen4bor6wvu

Automated Adversarial Testing of Unmodified Wireless Routing Implementations

Endadul Hoque, Hyojeong Lee, Rahul Potharaju, Charles Killian, Cristina Nita-Rotaru
2016 IEEE/ACM Transactions on Networking  
several additional attacks (e.g., replay attacks) and for establishment of adversarial side-channels that allow for collusion.  ...  Numerous routing protocols have been designed and subjected to model checking and simulations.  ...  However, such works do not consider adversarial environments as ours where we inject malicious faults that are tailored to imitate attackers.  ... 
doi:10.1109/tnet.2016.2520474 fatcat:ebxhobyaynczzb33ycocqf3iqu


Joanna Asia Biega, Krishna P. Gummadi, Ida Mele, Dragan Milchevski, Christos Tryfonopoulos, Gerhard Weikum
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
We cast these considerations into the new model of R-Susceptibility, which can inform and alert users about their potential for being targeted, and devise measures for quantitative risk assessment.  ...  We propose ranking as a means of modeling a rational adversary who targets the most afflicted users.  ...  Note that r-precision imitates an adversary who, for instance, knowing that 1% of the population is depressed, ranks the users according to a depression-risk measure and chooses the top 1% of the users  ... 
doi:10.1145/2911451.2911533 dblp:conf/sigir/BiegaGMMTW16 fatcat:pl4belusgjbnhficbjgqpeepgi

Query Answering for Existential Rules via Efficient Datalog Rewriting

Zhe Wang, Peng Xiao, Kewen Wang, Zhiqiang Zhuang, Hai Wan
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Existential rules are an expressive ontology formalism for ontology-mediated query answering and thus query answering is of high complexity, while several tractable fragments have been identified.  ...  In this paper, we fill the gap by proposing an efficient datalog rewriting approach for answering conjunctive queries over existential rules, and identify and combine existing fragments of existential  ...  Adversarial learning for recommendation.  ... 
doi:10.24963/ijcai.2020/264 dblp:conf/ijcai/ZhaoSZXB20 fatcat:binzkvxxmjeedhoeepxp6q57vu

Adversarial Ranking for Language Generation [article]

Kevin Lin, Dianqi Li, Xiaodong He, Zhengyou Zhang, Ming-Ting Sun
2018 arXiv   pre-print
In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions.  ...  Generative adversarial networks (GANs) have great successes on synthesizing data.  ...  Acknowledgement We would like to thank the reviewers for their constructive comments. We thank NVIDIA Corporation for the donation of the GPU used for this research.  ... 
arXiv:1705.11001v3 fatcat:d43f77emdjc5tooxeozv3l4qiu

Optimizing Interactive Systems with Data-Driven Objectives

Ziming Li
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
Effective optimization is essential for interactive systems to provide a satisfactory user experience. However, it is often challenging to find an objective to optimize for.  ...  It is promising if we model the objectives directly from the user interactions which we use to optimize interactive systems, which will improve user experience and dynamically reacts to user actions.  ...  domain-specific metrics, such as relevance judgements in information retrieval [22, 24, 47, 113, 114] , or user feedback (e.g., click, order, skip) in recommender systems [14, 159, 160] .  ... 
doi:10.24963/ijcai.2019/912 dblp:conf/ijcai/Li19 fatcat:km5f6bkjpjbenbpisskfm6iwta

The Impact of Semi-Supervised Learning on the Performance of Intelligent Chatbot System

Sudan Prasad Uprety, Seung Ryul Jeong
2022 Computers Materials & Continua  
the predictive performance of the proposed multi-domain intelligent chatbot over a base joint model and joint model based on adversarial learning.  ...  The key parts for such intelligent chatbot systems are domain classification, intent detection, and named entity recognition.  ...  The first idea of an HCI application comes from the Turing test or "imitation" game created by Alan Turing in 1950.  ... 
doi:10.32604/cmc.2022.023127 fatcat:mohe2hpgpzdmjdxwz32wiu4vtm

Deep Learning Techniques for Future Intelligent Cross-Media Retrieval [article]

Sadaqat ur Rehman, Muhammad Waqas, Shanshan Tu, Anis Koubaa, Obaid ur Rehman, Jawad Ahmad, Muhammad Hanif, Zhu Han
2020 arXiv   pre-print
Moreover, we also present an extensive review of the state-of-the-art problems and its corresponding solutions for encouraging deep learning in cross-media retrieval.  ...  Then, we present some well-known cross-media datasets used for retrieval, considering the importance of these datasets in the context in of deep learning based cross-media retrieval approaches.  ...  [112] proposed a novel adversarial model, called HashGAN.  ... 
arXiv:2008.01191v1 fatcat:t63bg55w2vdqjcprzaaidrmprq
« Previous Showing results 1 — 15 out of 623 results