{"title":"Opportunities for private and secure machine learning","authors":"Chris Clifton","doi":"10.1145/1456377.1456385","DOIUrl":"https://doi.org/10.1145/1456377.1456385","url":null,"abstract":"While the interplay of Artificial Intelligence and Security covers a wide variety of topics, the 2008 AISec program largely focuses on use of artificial intelligence techniques to aid with traditional security concerns: intrusion detection, security policy management, malware detection, etc. This talk will address the flip side of the issue: Using machine learning on sensitive data. The privacy-preserving data mining literature provides numerous solutions to machine learning on sensitive data, while protecting the data from disclosure. Unfortunately, privacy has yet to provide the economic incentives for commercial development of this technology. This talk will survey this work (and open challenges) in light of problems that may have greater incentives for development: collaborative machine learning by parties that do not fully trust each other. Opportunities include job brokerage (assigning jobs in ways that most efficiently utilize resources of competing companies), supply chain optimization, inter-agency data sharing, etc. Techniques similar to those in privacy-preserving data mining can enable such applications without the degree of information disclosure and trust currently required, providing a business model for development of the technology (and as a by-product, reducing the number of trusted systems that need to be secured.)","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132420090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Barreno, P. Bartlett, F. J. Chi, A. Joseph, B. Nelson, Benjamin I. P. Rubinstein, Udam Saini, J. D. Tygar
{"title":"Open problems in the security of learning","authors":"M. Barreno, P. Bartlett, F. J. Chi, A. Joseph, B. Nelson, Benjamin I. P. Rubinstein, Udam Saini, J. D. Tygar","doi":"10.1145/1456377.1456382","DOIUrl":"https://doi.org/10.1145/1456377.1456382","url":null,"abstract":"Machine learning has become a valuable tool for detecting and preventing malicious activity. However, as more applications employ machine learning techniques in adversarial decision-making situations, increasingly powerful attacks become possible against machine learning systems. In this paper, we present three broad research directions towards the end of developing truly secure learning. First, we suggest that finding bounds on adversarial influence is important to understand the limits of what an attacker can and cannot do to a learning system. Second, we investigate the value of adversarial capabilities-the success of an attack depends largely on what types of information and influence the attacker has. Finally, we propose directions in technologies for secure learning and suggest lines of investigation into secure techniques for learning in adversarial environments. We intend this paper to foster discussion about the security of machine learning, and we believe that the research directions we propose represent the most important directions to pursue in the quest for secure learning.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114954260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cognitive security for personal devices","authors":"R. Greenstadt, J. Beal","doi":"10.1145/1456377.1456383","DOIUrl":"https://doi.org/10.1145/1456377.1456383","url":null,"abstract":"Humans should be able to think of computers as extensions of their body, as craftsmen do with their tools. Current security models, however, are too unlike those used in human minds-for example, computers authenticate users by challenging them to repeat a secret rather than by continually observing the many subtle cues offered by their appearance and behavior. We propose two lines of research that can be combined to produce cognitive security on computers and other personal devices: continuously deployed multi-modal biometrics and adjustably autonomous security.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124540686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Kloft, Ulf Brefeld, Patrick Düssel, Christian Gehl, P. Laskov
{"title":"Automatic feature selection for anomaly detection","authors":"M. Kloft, Ulf Brefeld, Patrick Düssel, Christian Gehl, P. Laskov","doi":"10.1145/1456377.1456395","DOIUrl":"https://doi.org/10.1145/1456377.1456395","url":null,"abstract":"A frequent problem in anomaly detection is to decide among different feature sets to be used. For example, various features are known in network intrusion detection based on packet headers, content byte streams or application level protocol parsing. A method for automatic feature selection in anomaly detection is proposed which determines optimal mixture coefficients for various sets of features. The method generalizes the support vector data description (SVDD) and can be expressed as a semi-infinite linear program that can be solved with standard techniques. The case of a single feature set can be handled as a particular case of the proposed method. The experimental evaluation of the new method on unsanitized HTTP data demonstrates that detectors using automatically selected features attain competitive performance, while sparing practitioners from a priori decisions on feature sets to be used.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117088949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Urko Zurutuza, Roberto Uribeetxeberria, D. Zamboni
{"title":"A data mining approach for analysis of worm activity through automatic signature generation","authors":"Urko Zurutuza, Roberto Uribeetxeberria, D. Zamboni","doi":"10.1145/1456377.1456394","DOIUrl":"https://doi.org/10.1145/1456377.1456394","url":null,"abstract":"This paper proposes a novel framework to automatically discover and analyze traffic generated by computer worms and other anomalous behaviors that interact with a non-solicited traffic monitoring system. Network packets are analyzed by an Intrusion Detection System (IDS), and new signatures are generated clustering those which remain unknown for the IDS. Furthermore, the framework provides a mechanism to cluster the alarms produced by the IDS producing a correlated vision of the traffic observed. Both the automatic signature generation and the alarm clusters are accomplished using data mining techniques.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"835 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123292864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Patrick Gage Kelley, P. Drielsma, N. Sadeh, L. Cranor
{"title":"User-controllable learning of security and privacy policies","authors":"Patrick Gage Kelley, P. Drielsma, N. Sadeh, L. Cranor","doi":"10.1145/1456377.1456380","DOIUrl":"https://doi.org/10.1145/1456377.1456380","url":null,"abstract":"Studies have shown that users have great difficulty specifying their security and privacy policies in a variety of application domains. While machine learning techniques have successfully been used to refine models of user preferences, such as in recommender systems, they are generally configured as \"black boxes\" that take control over the entire policy and severely restrict the ways in which the user can manipulate it. This article presents an alternative approach, referred to as user-controllable policy learning. It involves the incremental manipulation of policies in a context where system and user refine a common policy model. The user regularly provides feedback on decisions made based on the current policy. This feedback is used to identify (learn) incremental policy improvements which are presented as suggestions to the user. The user, in turn, can review these suggestions and decide which, if any, to accept. The incremental nature of the suggestions enhances usability, and because the user and the system manipulate a common policy representation, the user retains control and can still make policy modifications by hand. Results obtained using a neighborhood search implementation of this approach are presented in the context of data derived from the deployment of a friend finder application, where users can share their locations with others, subject to privacy policies they refine over time. We present results showing policy accuracy, which averages 60% upon initial definition by our users climbing as high as 90% using our technique.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121953564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. L. Berral, Nicolás Poggi, Javier Alonso, Ricard Gavaldà, J. Torres, M. Parashar
{"title":"Adaptive distributed mechanism against flooding network attacks based on machine learning","authors":"J. L. Berral, Nicolás Poggi, Javier Alonso, Ricard Gavaldà, J. Torres, M. Parashar","doi":"10.1145/1456377.1456389","DOIUrl":"https://doi.org/10.1145/1456377.1456389","url":null,"abstract":"Adaptive techniques based on machine learning and data mining are gaining relevance in self-management and self-defense for networks and distributed systems. In this paper, we focus on early detection and stopping of distributed flooding attacks and network abuses. We extend the framework proposed by Zhang and Parashar (2006) to cooperatively detect and react to abnormal behaviors before the target machine collapses and network performance degrades. In this framework, nodes in an intermediate network share information about their local traffic observations, improving their global traffic perspective. In our proposal, we add to each node the ability of learning independently, therefore reacting differently according to its situation in the network and local traffic conditions. In particular, this frees the administrator from having to guess and manually set the parameters distinguishing attacks from non-attacks: now such thresholds are learned and set from experience or past data. We expect that our framework provides a faster detection and more accuracy in front of distributed flooding attacks than if static filters or single-machine adaptive mechanisms are used. We show simulations where indeed we observe a high rate of stopped attacks with minimum disturbance to the legitimate users.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123858268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Malware detection using adaptive data compression","authors":"Yan Zhou, M. Inge","doi":"10.1145/1456377.1456393","DOIUrl":"https://doi.org/10.1145/1456377.1456393","url":null,"abstract":"A popular approach in current commercial anti-malware software detects malicious programs by searching in the code of programs for scan strings that are byte sequences indicative of malicious code. The scan strings, also known as the signatures of existing malware, are extracted by malware analysts from known malware samples, and stored in a database often referred to as a virus dictionary. This process often involves a significant amount of human efforts. In addition, there are two major limitations in this technique. First, not all malicious programs have bit patterns that are evidence of their malicious nature. Therefore, some malware is not recorded in the virus dictionary and can not be detected through signature matching. Second, searching for specific bit patterns will not work on malware that can take many forms--obfuscated malware. Signature matching has been shown to be incapable of identifying new malware patterns and fails to recognize obfuscated malware. This paper presents a malware detection technique that discovers malware by means of a learning engine trained on a set of malware instances and a set of benign code instances. The learning engine uses an adaptive data compression model--prediction by partial matching (PPM)--to build two compression models, one from the malware instances and the other from the benign code instances. A code instance is classified, either as \"malware\" or \"benign\", by minimizing its estimated cross entropy. Our preliminary results are very promising. We achieved about 0.94 true positive rate with as low as 0.016 false positive rate. Our experiments also demonstrate that this technique can effectively detect unknown and obfuscated malware.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126870157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Robust content-driven reputation","authors":"K. Chatterjee, L. D. Alfaro, I. Pye","doi":"10.1145/1456377.1456387","DOIUrl":"https://doi.org/10.1145/1456377.1456387","url":null,"abstract":"In content-driven reputation systems for collaborative content, users gain or lose reputation according to how their contributions fare: authors of long-lived contributions gain reputation, while authors of reverted contributions lose reputation. Existing content-driven systems are prone to Sybil attacks, in which multiple identities, controlled by the same person, perform coordinated actions to increase their reputation. We show that content-driven reputation systems can be made resistant to such attacks by taking advantage of the fact that the reputation increments and decrements depend on content modifications, which are visible to all. We present an algorithm for content-driven reputation that prevents a set of identities from increasing their maximum reputation without doing any useful work. Here, work is considered useful if it causes content to evolve in a direction that is consistent with the actions of high-reputation users. We argue that the content modifications that require no effort, such as the insertion or deletion of arbitrary text, are invariably non-useful. We prove a truthfullness result for the resulting system, stating that users who wish to perform a contribution do not gain by employing complex contribution schemes, compared to simply performing the contribution at once. In particular, splitting the contribution in multiple portions, or employing the coordinated actions of multiple identities, do not yield additional reputation. Taken together, these results indicate that content-driven systems can be made robust with respect to Sybil attacks.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124081069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"POSH: a generalized captcha with security applications","authors":"Waseem Daher, R. Canetti","doi":"10.1145/1456377.1456379","DOIUrl":"https://doi.org/10.1145/1456377.1456379","url":null,"abstract":"A puzzle only solvable by humans, or POSH, is a prompt or question with three important properties: it can be generated by a computer, it can be answered consistently by a human, and a human answer cannot be efficiently predicted by a computer. In fact, unlike a CAPTCHA, a POSH does not necessarily have to be verifiable by a computer at all. One application of POSHes is a scheme proposed by Canetti et al.~that limits off-line dictionary attacks against password-protected local storage, without the use of any secure hardware or secret storage.\u0000 We explore the area of POSHes, implement several candidate POSHes and have users solve them, to evaluate their effectiveness. Given these data, we then implement the above scheme as an extension to the Mozilla Firefox web browser, where it is used to protect user certificates and saved passwords. In the course of doing so, we also define certain aspects of the threat model for our implementation (and the scheme) more precisely.","PeriodicalId":225009,"journal":{"name":"Security and Artificial Intelligence","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115462598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
