Facebook immune system

Stein, Tao; Chen, Erdong; Mangla, Karan

doi:10.1145/1989656.1989664

Cited by 170 publications

(129 citation statements)

References 5 publications

Supporting

Mentioning

127

Contrasting

Unclassified

Order By: Relevance

“…This affects "the metric interplay between fitness and immunity as response and detection latencies become more important than precision and recall". Damage accumulates quickly [53]. The above interplay and further analogies between AIS and IDS support evolution and co-evolution for both defense and offense whose role are interchangeable, and ultimately affect the effectiveness of the self-protection shield to buttress the defense.…”

Section: Immunity and Detectionmentioning

confidence: 92%

“…For completeness we mention that [53] have reported that they built and deployed a coherent, scalable, and extensible real time system, the Facebook Immune System (FIS), to protect users and the social graph (SG) they span. The use of "Immune" refers to overall defense against attackers (e.g., intruders similar to pathogens) without any specific adherence to AIS except a reference to generic mutation.…”

Section: Immunity and Detectionmentioning

confidence: 99%

“…The defender seeks to shorten Attack and Detection phases while lengthening the Defense and Mutate stages. The attacker seeks the opposite: to shorten Defense (by obscuring responses and subverting attack canaries) and Mutate while lengthening Attack and Detect" [53]. This illustrates why detection and response latencies are so important for effective defense with any AIS designed to shorten the phases controlled by attackers and to lengthen the phases under defense control.…”

Section: Immunity and Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Cyberspace Security Using Adversarial Learning and Conformal Prediction

Wechsler¹

2015

IIM

View full text Add to dashboard Cite

This paper advances new directions for cyber security using adversarial learning and conformal prediction in order to enhance network and computing services defenses against adaptive, malicious, persistent, and tactical offensive threats. Conformal prediction is the principled and unified adaptive and learning framework used to design, develop, and deploy a multi-faceted self-managing defensive shield to detect, disrupt, and deny intrusive attacks, hostile and malicious behavior, and subterfuge. Conformal prediction leverages apparent relationships between immunity and intrusion detection using non-conformity measures characteristic of affinity, a typicality, and surprise, to recognize patterns and messages as friend or foe and to respond to them accordingly. The solutions proffered throughout are built around active learning, meta-reasoning, randomness, distributed semantics and stratification, and most important and above all around adaptive Oracles. The motivation for using conformal prediction and its immediate off-spring, those of semi-supervised learning and transduction, comes from them first and foremost supporting discriminative and non-parametric methods characteristic of principled demarcation using cohorts and sensitivity analysis to hedge on the prediction outcomes including negative selection, on one side, and providing credibility and confidence indices that assist meta-reasoning and information fusion.

show abstract

Section: Immunity and Detectionmentioning

confidence: 92%

Section: Immunity and Detectionmentioning

confidence: 99%

Section: Immunity and Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Cyberspace Security Using Adversarial Learning and Conformal Prediction

Wechsler¹

2015

IIM

View full text Add to dashboard Cite

show abstract

“…Whatever the data in the form of numbers or texts has been extracted. 2) Then after extracting data from social media, splitter technique has been used here by considering space as separator [8]. 3) After that, concept of k-means algorithm has been used where different clusters of malicious keywords are created according to category [9].…”

Section: Proposed Methodologymentioning

confidence: 99%

“…Following up their work, Gao et al presented an online spam filtering system that could be deployed as a component of the OSN platform to inspect messages generated by users in real time [7]. Their approach focused on reconstructing spam messages into campaigns for classification rather than examining each post individually.…”

Section: Literature Reviewmentioning

confidence: 99%

Detection and Blocking Social Media Malicious Posts

2017

IJMTER

View full text Add to dashboard Cite

Abstract-Online Social Networks (OSNs) witness a rise in user activity whenever an event takes place. Malicious entities exploit this spur in user-engagement levels to spread malicious content that compromises system reputation and degrade user experience and has recently been reported to face much abuse through scams and other type of malicious content, especially during news making events. We have reached the era of social media networks represented by Facebook, Twitter, Flicker and YouTube. Internet users spend most of their time on social networks than search engines. Public figures and business entities set up social networking pages to promote direct interactions with the online users. Social media systems heavily depend on users for getting content and sharing. Information used is spread across the social networks in quick and effective manner. However, at the same time social media networks become vulnerable to different types of unwanted and malicious hacker or spammer actions. It has been observed that there is a greater participation in Facebook pages regarding malicious content generation. These contents will be in greater amount as compared to legitimate content. In this work we develop a detection mechanism to distinguish between malicious and genuine posts within seconds after the posts are uploaded by user. This work proposes an extensive way on the basis detection and blocking of malicious posts has been done.

show abstract

Understanding a prospective approach to designing malicious social bots

Zhang

et al. 2016

Security Comm Networks

View full text Add to dashboard Cite

The security implications of social bots are evident in consideration of the fact that data sharing and propagation functionality are well integrated with social media sites. Existing social bots primarily use Really Simple Syndication and OSN (online social network) application program interface to communicate with OSN servers. Researchers have profiled their behaviors well and have proposed various mechanisms to defend against them. We predict that a web test automation rootkit (WTAR) is a prospective approach for designing malicious social bots. In this paper, we first present the principles of designing WTAR-based social bots. Second, we implement three WTAR-based bot prototypes on Facebook, Twitter, and Weibo. Third, we validate this new threat by analyzing behaviors of the prototypes in a lab environment and on the Internet, and analyzing reports from widely-used antivirus software. Our analyses show that WTAR-based social bots have the following features: (i) they do not connect to OSN directly, and therefore produce few network flows; (ii) they can log in to OSNs easily and perform a variety of social activities; (iii) they can mimic the behaviors of a human user on an OSN. Finally, we propose several possible mechanisms in order to defend against WTAR-based social bots.

show abstract

Facebook immune system

Cited by 170 publications

References 5 publications

Cyberspace Security Using Adversarial Learning and Conformal Prediction

Cyberspace Security Using Adversarial Learning and Conformal Prediction

Detection and Blocking Social Media Malicious Posts

Understanding a prospective approach to designing malicious social bots

Contact Info

Product

Resources

About