2010 Proceeding- General Chair:
- Rachel Greenstadt
- Sponsor:
- sigsac
It is my great pleasure to welcome you to the 2010 ACM Workshop on Artificial Intelligence and Security -- AISec'10. This year's workshop continues its tradition of being a premier forum for presentation of research results and position papers that bridge the gap between the artificial intelligence and security communities. We also continue our relationship with the ACM Computer and Communications Security Conference (CCS 2010).
This will be the third workshop on Security and Artificial Intelligence. Techniques from artificial intelligence (notably bayesian learning and captchas) have achieved great success in helping administrators manage automated attacks such as SPAM and network attacks that would overwhelm human capacities. The proliferation of data and data mining techniques has important implications for security and privacy. However, the scientific foundation for the use of these techniques in adversarial contexts contains many open questions, other AI techniques are being applied to security applications, and as AI technologies (like autonomous vehicles) become increasingly mainstream, their security properties become increasingly important.
The call for papers attracted 15 submissions from 6 countries on 3 continents. The program committee accepted 5 full papers and 5 short papers that cover a variety of security applications from malware detection to social network privacy and use a variety of AI techniques from machine learning to adjustable autonomy.
Proceeding Downloads
Towards modeling the behavior of physical intruders in a region monitored by a wireless sensor network
A priority task for homeland security is the coverage of large spans of open border that cannot be continuously physically monitored for intrusion. Low-cost monitoring solutions based on wireless sensor networks have been identified as an effective ...
Eliminating routing protocol anomalies in wireless sensor networks using AI techniques
The specific nature of routing in sensor networks has made possible new sorts of attacks that can have closer insight and effect on the networks packets, the most important being the packet tampering. Routing attacks on the network level are the first ...
Empirical evaluation of authorship obfuscation using JGAAP
Authorship attribution is an important emerging security tool. However, just as criminals may wear gloves to hide their fingerprints, so authors may choose to mask their style to escape detection. Most authorship studies have focused on cooperative and/...
Towards security policy decisions based on context profiling
With the increasing popularity of personal mobile devices like smartphones, more and more ordinary users create and consume valuable, private and sensitive data such as photos, videos, messages, documents as well as access credentials for various ...
The limits of automatic OS fingerprint generation
Remote operating system fingerprinting relies on implementation differences between OSs to identify the specific variant executing on a remote host. Because these differences can be subtle and difficult to find, most fingerprinting tools require expert ...
Relational network-service clustering analysis with set evidences
Network administrators are faced with a large amount of network data that they need to sift through to analyze user behaviors and detect anomalies. Through a network monitoring tool, we obtained TCP and UDP connection records together with additional ...
Synthetic security policy generation via network traffic clustering
Security policies are an essential part in the operations of any networking system. Test policies are always needed for conducting research and development. Such policies are required in various phases of research related to many problems as performance ...
Lexical feature based phishing URL detection using online learning
Phishing is a form of cybercrime where spammed emails and fraudulent websites entice victims to provide sensitive information to the phishers. The acquired sensitive information is subsequently used to steal identities or gain access to money. This ...
Cheap and automated socio-technical attacks based on social networking sites
The vastly and steadily increasing data pool collected by social networking sites can have severe implications once this information becomes available to attackers. Whilst socio-technical attacks such as social engineering relied upon expensive ...
Adjustable autonomy for cross-domain entitlement decisions
Cross-domain information exchange is a growing problem, as business and governmental organizations increasingly need to integrate their information systems with those of partially trusted partners. Current identity management and access control ...