security and trust in social media networks · multimedia signal processing group swiss federal...
TRANSCRIPT
![Page 1: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/1.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!1
Prof. Touradj Ebrahimi [email protected]
!DMP meeting
San Jose, CA, USA 11 January 2014
Security and Trust in social media networks
![Page 2: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/2.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!2Social media landscape
http://www.fredcavazza.net/2012/02/22/social-media-landscape-2012/
![Page 3: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/3.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!3Popularity of social networks
http://blog.tweetsmarter.com/social-media/spring-2012-social-media-user-statistics/
May 2012
March 2012
![Page 4: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/4.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
1+ billion photos
~140 billion photos
7+ billion photos
Popularity of social networks (cont.)
72 hours of videoevery minute
April 2012
![Page 5: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/5.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!5Popularity of social networks (cont.)
http://www.trendweek.com/en/60-seconds-of-social-media-sharing/
February 2012
![Page 6: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/6.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!6Popularity of social networks (cont.)
http://online.wsj.com/article/SB10001424052970204653604577249341403742390.html
January 2012
![Page 7: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/7.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
Trust & security issues in social networks !7
![Page 8: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/8.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!8
• Socialcam application automatically shares with your Facebook friends videos you watch
• May be doing you more harm than good!
Trust & security issues in social networks (cont.)
![Page 9: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/9.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!9
• Spotify and Yahoo News Activity automatically publish songs and news you have listened to or read on your profile page
Trust & security issues in social networks (cont.)
![Page 10: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/10.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!10
• “Responsible” sharing (e.g. a friend posted an embarrassing photo of a young political candidate Emma Kiernan enjoying a party)
Trust & security issues in social networks (cont.)
http://newsbizarre.com/2009/05/emma-kiernan-facebook-photo-puts-young.html
Anybody can post any picture of you on Facebook at any time! Even if deleted, it is there forever, stored in the vast Internet memory bank to be found again and again!
![Page 11: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/11.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!11
• “Responsible” sharing (e.g. top model Rosanagh Wypych posted photos of her and friends drinking alcohol and consuming cannabis)
Trust & security issues in social networks (cont.)
http://www.3news.co.nz/Top-Model-Rosanagh-worried-after-Facebook-pot-pic/tabid/418/articleID/224047/Default.aspx
![Page 12: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/12.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!12Trust & security issues in social networks (cont.)
Only around 50% of tags are truly related to an image[Kennedy et al., ACM MIR 2006]
!Challenges: • Identify the most
appropriate tags • Eliminate noisy
or spam tags
• Wrong tags in Flickr
![Page 13: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/13.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!13
• Spam bookmarks in Delicious
Trust & security issues in social networks (cont.)
![Page 14: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/14.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
Trust & security solutions in social networks !14
![Page 15: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/15.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!15
• Limit number of people to share content and communications with – create private groups (e.g. Google+ Circles, Facebook Smart Lists)
Trust & security solutions in social networks (cont.)
![Page 16: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/16.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!16
• Limit time to watch shared content(e.g. SnapChat application – though they are not able to guarantee that your messaging datawill be deleted in all instances)
Trust & security solutions in social networks (cont.)
![Page 17: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/17.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!17
• Manage your account (friends, photos, comments, posts) • Make sure that what you are sharing or posting is not going
to cause regret
Trust & security solutions in social networks (cont.)
http://www.huffingtonpost.com/2012/03/20/social-media-privacy-infographic_n_1367223.html
![Page 18: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/18.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!18
• E-mail !
• Web search !
• Web videos !
• Blogs !
• Online shopping systems !
• Peer-to-peer (P2P) networks
Trust & security before social media
![Page 19: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/19.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!19Anti-spam strategies in online systems
[Heymann, Koutrika, Garcia-Molina, IEEE IC 2007]
![Page 20: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/20.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!20Trust and reputation online systems
![Page 21: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/21.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!21Trust and reputation online systems (cont.)
Email spam filtering
![Page 22: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/22.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!22Model of social tagging system
[Ivanov, Vajda, Lee, Ebrahimi, IEEE SPM 2012]
![Page 23: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/23.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!23Categorization of trust models
[Ivanov, Vajda, Lee, Ebrahimi, IEEE SPM 2012]
![Page 24: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/24.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!24
• User trust modeling is more popular than content trust modeling: • User trust models has a less complexity than content trust models • User trust models can quickly adapt to the constantly evolving and
changing environment in social systems due to the type of features used for modeling, and thus be applicable longer than content trust models, without need for creation of new models
• User trust modeling has a disadvantage of “broad brush”, i.e. it may be excessively strict if a user happens to post one bit of questionable content on otherwise legitimate content
• “Subjectivity” in classifying spam and non-spam content/users remains as a fundamental issue, i.e. what is spam content/user to one person may be interesting to another one
User versus content trust modeling
![Page 25: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/25.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!25Summary of representative recent techniquesReference Trust
modelMedia Method Dataset
Gyongyi et al. 2004
content web pages an iterative approach, called TrustRank, to propagate trust scores to all nodes in the graph by splitting the trust score of a node among its neighbors according to a weighting scheme
AltaVista,real
Koutrika et al. 2008
content bookmarks a coincidence-based model for query-by-tag search which estimates the level of agreement among different users in the system for a given tag
Delicious,real & simulated
Wu et al. 2005
content images a computer vision technique based on low-level image features to detect embedded text and computer-generated graphics
SpamArchive & Ling-Spam,real
Liu et al. 2009
content & user
bookmarks an iterative approach to identify spam content by its information value extracted from the collaborative knowledge
Delicious,real
Bogers and Van den Bosch 2008
content & user
bookmarks KL-divergence to measure the similarity between language models and new posts
BibSonomy & CiteULike,real
Ivanov et al. 2012
user images an approach based on the feedback from other users who agree or disagree with a tag associated with an image
Panoramio,real
[Ivanov, Vajda, Lee, Ebrahimi, IEEE SPM 2012]
![Page 26: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/26.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!26Summary of representative recent techniques (cont.)Reference Trust
modelMedia Method Dataset
Xu et al. 2006
user bookmarks an iterative approach to compute the goodness of each tag with respect to a content and the authority scores of the users
MyWeb 2.0,real
Krestel and Chen 2008
user bookmarks a TrustRank-based approach using features which model tag co-occurance, content co-occurance and co-occurance of tag-content
BibSonomy,real
Benevenuto et al. 2009
user videos a supervised learning approach applied on features that reflect users behavior through video responses
YouTube,real
Lee et al. 2010
user tweets a machine learning approach applied on social honeypots including users’ profile and tweets’ features
Twitter,real & simulated
Krause et al. 2008
user bookmarks a machine learning approach applied on a user’s profile, bookmarking activity and context of tags features
BibSonomy,real
Markines et al. 2009
user bookmarks a machine learning approach applied on tag-, content- and user-based features
BibSonomy,real
Caverlee et al. 2008
user user profiles
an approach to compute a dynamic trust score, called SocialTrust, depending on the quality of the relationship and personalized feedback ratings
MySpace,real
[Ivanov, Vajda, Lee, Ebrahimi, IEEE SPM 2012]
![Page 27: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/27.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!27
• Publicly available datasets: • Publication of datasets from different social networks and even
different datasets of one social network for evaluation of trust modeling approaches is rarely found, which makes it difficult to compare results and performance ofdifferent trust models
• Most of the datasets provide data for evaluatingonly one aspect of trust modeling, eitheruser or content trust modeling, while evaluation of the other aspect requires introducing simulated objects in the real-world socialtagging datasets
Open issues & challenges
![Page 28: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/28.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!28
• Dynamics of trust: • User’s trust tends to vary over time according to the user’s
experience and evolvement of social networks • Only a few approaches deal with dynamics of trust by distinguishing
between recent and old tags
Open issues & challenges (cont.)
![Page 29: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/29.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!29
• Multilingualism: • Most of the existing trust modeling approaches based on text
information assume monolingual environments • Some text information may be regarded as wrong due to the
language difference – people from various countries, so various languages simultaneously appear in tags and comments
Open issues & challenges (cont.)
![Page 30: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/30.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!30
• Interaction across social networks: • How trust models across domains can be effectively connected
and shared? E.g. users can use their Facebook accounts to log in some other social network services
Open issues & challenges (cont.)
![Page 31: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/31.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!31
• Multimodal analysis: • Most of the current techniques for noise and spam reduction focus
only on textual tag processing and user profile analysis, while audio and visual content features of multimedia content can also provide useful information about the relevance of the content and content-tag relationship
Open issues & challenges (cont.)
![Page 32: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/32.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!32
B. Sigurbjornsson, and R. van Zwol, "Flickr tag recommendation based on collective knowledge," in Proc. WWW, Apr. 2008, pp. 327–336.
L. S. Kennedy, S.-F. Chang, and I. V. Kozintsev, “To search or to label?: Predicting the performance of search-based automatic image classifiers,” in Proc. ACM MIR, Oct. 2006, pp. 249–258.
K. Liu, B. Fang, and Y. Zhang, “Detecting tag spam in social tagging systems with collaborative knowledge,” in Proc. IEEE FSKD, Aug. 2009, pp. 427–431.
P. Heymann, G. Koutrika, and H. Garcia-Molina, “Fighting spam on social web sites: A survey of approaches and future challenges,” IEEE Internet Comput., vol. 11, no. 6, pp. 36–45, Nov. 2007.
X. Li, C. Snoek, and M. Worring, "Learning tag relevance by neighbor voting for social image retrieval," in Proc. ACM MIR, Oct. 2008, pp. 180-187.
B. Markines, C. Cattuto, and F. Menczer, “Social spam detection,” in Proc. ACM AIRWeb, Apr. 2009, pp. 41–48.
B. Krause, C. Schmitz, A. Hotho, and Stum G., “The anti-social tagger: Detecting spam in social bookmarking systems,” in Proc. ACM AIRWeb, Apr. 2008, pp. 61–68.
G. Koutrika, F. A. Effendi, Z. Gyongyi, P. Heymann, and H. Garcia-Molina, “Combating spam in tagging systems: An evaluation,” ACM TWEB, vol. 2, no. 4, pp. 22:1–22:34, Oct. 2008.
Z. Gyongyi, H. Garcia-Molina, and J. Pedersen, “Combating web spam with TrustRank,” in Proc. VLDB, Aug. 2004, pp. 576–587.
C.-T. Wu, K.-T. Cheng, Q. Zhu, and Y.-L. Wu, “Using visual features for anti-spam filtering,” in Proc. IEEE ICIP, Sep. 2005, vol. 3, pp. III – 509–512.
References
![Page 33: Security and Trust in social media networks · Multimedia Signal Processing Group Swiss Federal Institute of Technology!24 • User trust modeling is more popular than content trust](https://reader034.vdocuments.us/reader034/viewer/2022043023/5f3f4527b21d575600633e57/html5/thumbnails/33.jpg)
Multimedia Signal Processing Group Swiss Federal Institute of Technology
!33
I. Ivanov, P. Vajda, J.-S. Lee, and T. Ebrahimi, "In tags we trust: Trust modeling in social tagging of multimedia content," in IEEE SPM, vol. 29, no. 2, pp. 98-107, Mar. 2012.
I. Ivanov, P. Vajda, J.-S. Lee, L. Goldmann, and T. Ebrahimi, “Geotag propagation in social networks based on user trust model,” MTAP, vol. 56, no. 1, pp. 155-177, Jan. 2012.
I. Ivanov, P. Vajda, L. Goldmann, J.-S. Lee, and T. Ebrahimi, "Object-based tag propagation for semi-automatic annotation of images," in Proc. ACM MIR, Mar. 2010, pp. 497-506.
T. Bogers and A. Van den Bosch, “Using language models for spam detection in social bookmarking,” in Proc. ECML PKDD, Sep. 2008, pp. 1–12.
Z. Xu, Y. Fu, J. Mao, and D. Su, “Towards the semantic web: Collaborative tag suggestions,” in Proc. ACM WWW, May 2006.
R. Krestel and L. Chen, “Using co-occurence of tags and resources to identify spammers,” in Proc. ECML PKDD, Sep. 2008, pp. 38–46.
F. Benevenuto, T. Rodrigues, V. Almeida, J. Almeida, and M. Gonc¸alves, “Detecting spammers and content promoters in online video social networks,” in Proc. ACM SIGIR, Jul. 2009, pp. 620–627.
K. Lee, J. Caverlee, and S. Webb, “Uncovering social spammers: social honeypots + machine learning,” in Proc. ACM SIGIR, Jul. 2010, pp. 435–442.
M. G. Noll, C. A. Yeung, N. Gibbins, C. Meinel, and N. Shadbolt, “Telling experts from spammers: Expertise ranking in folksonomies,” in Proc. ACM SIGIR, Jul. 2009, pp. 612–619.
J. Caverlee, L. Liu, and S. Webb, “SocialTrust: Tamper-resilient trust establishment in online communities,” in Proc. ACM JCDL, Jun. 2008, pp. 104–114.
A. Hotho, D. Benz, R. J¨aschke, and B. Krause, Eds., ECML PKDD Discovery Challenge, Sep. 2008, Available at: http://www.kde.cs.uni-kassel.de/ws/rsdc08.
References (cont.)