English
Related papers

Related papers: Hack The Box: Fooling Deep Learning Abstraction-Ba…

200 papers

In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary…

Machine Learning · Computer Science 2019-01-17 Sebastian Kauschke , David Hermann Lehmann

Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce unintuitive outputs. One key approach to verify and mitigate such robustness issues is to falsify…

Cryptography and Security · Computer Science 2025-10-07 Raik Dankworth , Gesina Schwalbe

Novelty detection is crucial for real-life applications. While it is common in activity recognition to assume a closed-set setting, i.e. test samples are always of training categories, this assumption is impractical in a real-world…

Computer Vision and Pattern Recognition · Computer Science 2018-10-31 Alina Roitberg , Ziad Al-Halah , Rainer Stiefelhagen

Anomaly detection, a.k.a. outlier detection or novelty detection, has been a lasting yet active research area in various research communities for several decades. There are still some unique problem complexities and challenges that require…

Machine Learning · Computer Science 2020-12-08 Guansong Pang , Chunhua Shen , Longbing Cao , Anton van den Hengel

Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world…

Machine Learning · Computer Science 2019-01-15 Mingxiao An , Yongzhou Chen , Qi Liu , Chuanren Liu , Guangyi Lv , Fangzhao Wu , Jianhui Ma

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

Machine Learning · Computer Science 2019-10-23 Saeid Samizade , Zheng-Hua Tan , Chao Shen , Xiaohong Guan

Deep learning systems are known to be vulnerable to adversarial examples. In particular, query-based black-box attacks do not require knowledge of the deep learning model, but can compute adversarial examples over the network by submitting…

Cryptography and Security · Computer Science 2022-06-10 Huiying Li , Shawn Shan , Emily Wenger , Jiayun Zhang , Haitao Zheng , Ben Y. Zhao

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…

Machine Learning · Statistics 2017-03-23 Giorgio Patrini , Alessandro Rozza , Aditya Menon , Richard Nock , Lizhen Qu

Active learning approaches in computer vision generally involve querying strong labels for data. However, previous works have shown that weak supervision can be effective in training models for vision tasks while greatly reducing annotation…

Computer Vision and Pattern Recognition · Computer Science 2019-10-16 Sai Vikas Desai , Akshay L Chandra , Wei Guo , Seishi Ninomiya , Vineeth N Balasubramanian

In real applications, object detectors based on deep networks still face challenges of the large domain gap between the labeled training data and unlabeled testing data. To reduce the gap, recent techniques are proposed by aligning the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-07 Sanli Tang , Zhanzhan Cheng , Shiliang Pu , Dashan Guo , Yi Niu , Fei Wu

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency.…

Machine Learning · Computer Science 2022-06-07 Zeyu Dai , Shengcai Liu , Ke Tang , Qing Li

Deep neural network (DNN) architecture based models have high expressive power and learning capacity. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within…

Computer Vision and Pattern Recognition · Computer Science 2018-03-02 Gaurav Goswami , Nalini Ratha , Akshay Agarwal , Richa Singh , Mayank Vatsa

Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to…

Cryptography and Security · Computer Science 2020-01-01 Xiaoyu Cao , Neil Zhenqiang Gong

Botnet detection based on machine learning have witnessed significant leaps in recent years, with the availability of large and reliable datasets that are extracted from real-life scenarios. Consequently, adversarial attacks on machine…

Cryptography and Security · Computer Science 2023-10-03 Mohammed M. Alani , Atefeh Mashatan , Ali Miri

Blind spots or outright deceit can bedevil and deceive machine learning models. Unidentified objects such as digital "stickers," also known as adversarial patches, can fool facial recognition systems, surveillance systems and self-driving…

Computer Vision and Pattern Recognition · Computer Science 2021-10-01 Zijian Zhu , Hang Su , Chang Liu , Wenzhao Xiang , Shibao Zheng

Object detectors are typically trained once and for all on a fixed set of classes. However, this closed-world assumption is unrealistic in practice, as new classes will inevitably emerge after the detector is deployed in the wild. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Tyler L. Hayes , César R. de Souza , Namil Kim , Jiwon Kim , Riccardo Volpi , Diane Larlus

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Machine Learning · Computer Science 2020-07-13 Anh Bui , Trung Le , He Zhao , Paul Montague , Olivier deVel , Tamas Abraham , Dinh Phung

Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater…

Machine Learning · Computer Science 2019-08-30 Ling Liu , Wenqi Wei , Ka-Ho Chow , Margaret Loper , Emre Gursoy , Stacey Truex , Yanzhao Wu

Deep learning models for image classification have become standard tools in recent years. A well known vulnerability of these models is their susceptibility to adversarial examples. These are generated by slightly altering an image of a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-08 Haim Fisher , Moni Shahar , Yehezkel S. Resheff