Search Results - "Molloy, Ian"

PAKDD’12 best paper: generating balanced classifier-independent training samples from unlabeled data by Park, Youngja, Qi, Zijie, Chari, Suresh N., Molloy, Ian M.

“…We consider the problem of generating balanced training samples from an unlabeled data set with an unknown class distribution. While random sampling works well…”
Get full text

Slicing: A New Approach for Privacy Preserving Data Publishing by Tiancheng Li, Ninghui Li, Jian Zhang, Molloy, I.

“…Several anonymization techniques, such as generalization and bucketization, have been designed for privacy preserving microdata publishing. Recent work has…”
Get full text

Backdoor smoothing: Demystifying backdoor attacks on deep neural networks by Grosse, Kathrin, Lee, Taesung, Biggio, Battista, Park, Youngja, Backes, Michael, Molloy, Ian

“…Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require…”
Get full text

AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos by Xiao, Chaowei, Deng, Ruizhi, Li, Bo, Lee, Taesung, Edwards, Benjamin, Yi, Jinfeng, Song, Dawn, Liu, Mingyan, Molloy, Ian

“…Deep neural networks (DNNs) have been widely applied in various applications, including autonomous driving and surveillance systems. However, DNNs are found to…”
Get full text

On the (In)Security and (Im)Practicality of Outsourcing Precise Association Rule Mining by Molloy, I., Ninghui Li, Tiancheng Li

“…The recent interest in outsourcing IT services onto the cloud raises two main concerns: security and cost. One task that could be outsourced is data mining. In…”
Get full text

Reaching Data Confidentiality and Model Accountability on the CalTrain by Gu, Zhongshu, Jamjoom, Hani, Su, Dong, Huang, Heqing, Zhang, Jialong, Ma, Tengfei, Pendarakis, Dimitrios, Molloy, Ian

“…Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusted multi-party participants. Data confidentiality…”
Get full text

A Large-Scale Study of Android Malware Development Phenomenon on Public Malware Submission and Scanning Platform by Huang, Heqing, Zheng, Cong, Zeng, Junyuan, Zhou, Wu, Zhu, Sencun, Liu, Peng, Molloy, Ian, Chari, Suresh, Zhang, Ce, Guan, Quanlong

“…With the steady growth of Android malware, we suspect that, during the malware development phase, some Android malware writers use the popular public scanning…”
Get full text

Web Service for extracting stream networks from DEM data by Luo, Wei, Li, Xiaoyan, Molloy, Ian, Di, Liping, Stepinski, Tomasz

“…This paper describes the implementation of a morphology based algorithm for extracting stream networks from data as a Web Service within the framework of…”
Get full text

Generating Summary Risk Scores for Mobile Applications by Gates, Christopher S., Ninghui Li, Hao Peng, Sarma, Bhaskar, Yuan Qi, Potharaju, Rahul, Nita-Rotaru, Cristina, Molloy, Ian

“…One of Android's main defense mechanisms against malicious apps is a risk communication mechanism which, before a user installs an app, warns the user about…”
Get full text

URET: Universal Robustness Evaluation Toolkit (for Evasion) by Eykholt, Kevin, Lee, Taesung, Schales, Douglas, Jang, Jiyong, Molloy, Ian, Zorin, Masha

“…Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such…”
Get full text

Learning Stochastic Models of Information Flow by Dickens, L., Molloy, I., Lobo, J., Pau-Chen Cheng, Russo, A.

“…An understanding of information flow has many applications, including for maximizing marketing impact on social media, limiting malware propagation, and…”
Get full text

Defending Against Neural Network Model Stealing Attacks Using Deceptive Perturbations by Lee, Taesung, Edwards, Benjamin, Molloy, Ian, Su, Dong

“…Machine learning architectures are readily available, but obtaining the high quality labeled data for training is costly. Pre-trained models available as cloud…”
Get full text

Adaptive Verifiable Training Using Pairwise Class Similarity by Wang, Shiqi, Eykholt, Kevin, Lee, Taesung, Jang, Jiyong, Molloy, Ian

“…Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single…”
Get full text

Adversarial Examples and Metrics by Döttling, Nico, Grosse, Kathrin, Backes, Michael, Molloy, Ian

“…Adversarial examples are a type of attack on machine learning (ML) systems which cause misclassification of inputs. Achieving robustness against adversarial…”
Get full text

All Your Alexa Are Belong to Us: A Remote Voice Control Attack against Echo by Xuejing Yuan, Yuxuan Chen, Aohui Wang, Kai Chen, Shengzhi Zhang, Heqing Huang, Molloy, Ian M.

“…Voice controlled system becomes increasingly popular these days due to the convenient and natural control over lots of functionalities and smart devices…”
Get full text

IDIoT: Securing the Internet of Things like it's 1994 by Barrera, David, Molloy, Ian, Huang, Heqing

“…Over 20 billion Internet of Things devices are set to come online by 2020. Protecting such a large number of underpowered, UI-less, network-connected devices…”
Get full text

Automatic migration to role based access control by Molloy, Ian M

“…The success of role-based access control both within the research community and industry is undeniable. One of the main reasons for RBAC’s adoption is its…”
Get full text

Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networks by Grosse, Kathrin, Lee, Taesung, Biggio, Battista, Park, Youngja, Backes, Michael, Molloy, Ian

“…Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require…”
Get full text

Defending Against Machine Learning Model Stealing Attacks Using Deceptive Perturbations by Lee, Taesung, Edwards, Benjamin, Molloy, Ian, Su, Dong

“…Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these…”
Get full text

Reaching Data Confidentiality and Model Accountability on the CalTrain by Gu, Zhongshu, Jamjoom, Hani, Su, Dong, Huang, Heqing, Zhang, Jialong, Ma, Tengfei, Pendarakis, Dimitrios, Molloy, Ian

“…Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusting multi-party participants. Data…”
Get full text