ML p(r)ior | I Know What You Saw Last Minute - Encrypted HTTP Adaptive Video Streaming Title Classification

I Know What You Saw Last Minute - Encrypted HTTP Adaptive Video Streaming Title Classification

2016-02-01
1602.00490 | cs.MM
Desktops and laptops can be maliciously exploited to violate privacy. There are two main types of attack scenarios: active and passive. In this paper, we consider the passive scenario where the adversary does not interact actively with the device, but he is able to eavesdrop on the network traffic of the device from the network side. Most of the Internet traffic is encrypted and thus passive attacks are challenging. Previous research has shown that information can be extracted from encrypted multimedia streams. This includes video title classification of non HTTP adaptive streams (non-HAS). This paper presents an algorithm for encrypted HTTP adaptive video streaming title classification. We show that an external attacker can identify the video title from video HTTP adaptive streams (HAS) sites such as YouTube. To the best of our knowledge, this is the first work that shows this. We provide a large data set of 10000 YouTube video streams of 100 popular video titles (each title downloaded 100 times) as examples for this task. The dataset was collected under real-world network conditions. We present several machine algorithms for the task and run a through set of experiments, which shows that our classification accuracy is more than 95%. We also show that our algorithms are able to classify video titles that are not in the training set as unknown and some of the algorithms are also able to eliminate false prediction of video titles and instead report unknown. Finally, we evaluate our algorithms robustness to delays and packet losses at test time and show that a solution that uses SVM is the most robust against these changes given enough training data. We provide the dataset and the crawler for future research.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2017-05-22
1705.07750 | cs.CV

The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it di… show more
PDF

Highlights - Most important sentences from the article

2018-10-14

Neural message passing algorithms for semi-supervised classification on graphs have recently achieve… show more
PDF

Highlights - Most important sentences from the article

2016-09-29

Convolutional Neural Networks (CNNs) have proven very effective in image classification and show pro… show more
PDF

Highlights - Most important sentences from the article

2018-06-19

Diverse input data modalities can provide complementary cues for several tasks, usually leading to m… show more
PDF

Highlights - Most important sentences from the article

2017-12-14

We propose a weakly supervised temporal action localization algorithm on untrimmed videos using conv… show more
PDF

Highlights - Most important sentences from the article

2018-07-27

Most activity localization methods in the literature suffer from the burden of frame-wise annotation… show more
PDF

Highlights - Most important sentences from the article

2017-11-11
1711.04161 | cs.CV

From the frame/clip-level feature learning to the video-level representation building, deep learning… show more
PDF

Highlights - Most important sentences from the article

2017-06-17

The YouTube-8M video classification challenge requires teams to classify 0.7 million videos into one… show more
PDF

Highlights - Most important sentences from the article

2018-06-19
1806.07506 | cs.SD

In the past, Acoustic Scene Classification systems have been based on hand crafting audio features t… show more
PDF

Highlights - Most important sentences from the article

2017-04-25
1704.07657 | cs.LG

Various modifications of decision trees have been extensively used during the past years due to thei… show more
PDF

Highlights - Most important sentences from the article

2019-04-16

We introduce a self-supervised representation learning method based on the task of temporal alignmen… show more
PDF

Highlights - Most important sentences from the article

2019-01-13

In the authors' opinion, anomaly detection systems, or ADS, seem to be the most perspective directio… show more
PDF

Highlights - Most important sentences from the article

2019-04-04

Our understanding and ability to effectively monitor and manage coastal ecosystems are severely limi… show more
PDF

Highlights - Most important sentences from the article

2019-01-10

Mobile video traffic is dominant in cellular and enterprise wireless networks. With the advent of di… show more
PDF

Highlights - Most important sentences from the article

2018-11-15

Existing reinforcement learning~(RL)-based adaptive bitrate~(ABR) approaches outperform the previous… show more
PDF

Highlights - Most important sentences from the article