Near-optimal Evasion of Randomized Convex-inducing Classifiers in Adversarial Environments | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=Gbul4Ykj8Eo


Duration: 1:00:35
167 views
5

For slides and more information on the paper, visit https://aisc.a-i.science/events/2019-05-23

Discussion lead: Pooria Madani


Motivation:
Classifiers are often used to detect malicious activities in adversarial environments. Sophisticated adversaries would attempt to find information about deployed classifiers in order to strategies different evasion techniques. It is a widely held belief that randomization of decision boundaries/rules of detection systems would introduce further complexities in attempts made by the adversaries for finding minimal adversarial cost (MAC) evading instances. We have extended the results obtained by Nelson et al. [14] and further presented a novel algorithm that can find optimal evading instances in randomized convex-inducing classifiers using polynomial-many queries. Our results have demonstrated that the complexity introduced through randomization only increases the complexity of finding an optimal evading instance by a constant factor and thus the risk of optimal evasion is still present.



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2019-07-02Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
2019-06-26Neural Models of Text Normalization for Speech Applications | AISC Author Speaking
2019-06-24Assessing Modeling Variability in Autonomous Vehicle Accelerated Evaluation
2019-06-20AISC Abstract Night June 20 2019
2019-06-17Learnability can be undecidable | AISC
2019-06-10Speech synthesis from neural decoding of spoken sentences | AISC
2019-06-06Swim Stroke Analytic: Front Crawl Pulling Pose Classification | AISC
2019-06-05State of Natural Language Processing in 2019 | AISC
2019-06-03Superposition of Many Models into One | AISC
2019-05-27Learning Discrete Structures for Graph Neural Networks | AISC
2019-05-23Near-optimal Evasion of Randomized Convex-inducing Classifiers in Adversarial Environments | AISC
2019-05-21Comparative Document Summarisation via Classification | AISC
2019-05-13Sparse Transformers and MuseNet | AISC
2019-05-09Content Tree Word Embedding for document representation | AISC
2019-05-06Deep Temporal Logistic Bag-of-Features For Forecasting High Frequency Limit Order Book Time Series
2019-05-02A Web-scale system for scientific knowledge exploration | AISC
2019-05-02Convolutional Neural Networks for processing EEG signals
2019-05-02Classification of sentiment reviews using n-gram machine learning approach
2019-05-02Introduction to the Conditional GAN - A General Framework for Pixel2Pixel Translation
2019-05-02A Style-Based Generator Architecture for Generative Adversarial Networks
2019-05-02A Framework for Developing Deep Learning Classification Models