- Sponsor:
- sigsac
It is our great pleasure to welcome you to the 2nd ACM Workshop on AISec -- AISec 2009. The mission of this new workshop is to stimulate increased collaboration between the Security and AI communities. It is our strong belief that such collaboration is the best route towards fully realizing the security and privacy benefits of today's ubiquitous information.
The call for papers attracted 24 submissions from Asia, Europe and the United States. The program committee accepted 10 papers covering a variety of topics, including privacy in social networking sites, malware and network attack defense, and reputation systems.
Proceeding Downloads
A framework for quantitative security analysis of machine learning
We propose a framework for quantitative security analysis of machine learning methods. The key parts of this framework are the formal specification of a deployed learning model and attacker's constraints, the computation of an optimal attack, and the ...
Inferring privacy policies for social networking services
Social networking sites have come under criticism for their poor privacy protection track record. Yet, there is an inherent difficulty in deciding which principals should have access to user's information or actions, without requiring them to constantly ...
Finding "hidden" connections on linkedIn an argument for more pragmatic social network privacy
Social networking services well know that some users are unwilling to freely share the information they store with the service (e.g. profile information). To address this, ser vices typically provide various privacy "knobs" that the user may adjust to ...
Captcha-free throttling
We argue that the CAPTCHA in its current incarnation may be near the end of its useful life, and propose an alternative throttling mechanism to control access to web resources. We analyze our proposed solution against a collection of realistic ...
P2P botnet detection using behavior clustering & statistical tests
Botnets are widely believed to be the most serious danger to the Internet. Most recent research on botnet detection focuses on centralized botnets and primarily relies on two assumptions: prior knowledge of potential C&C channels and capability of ...
Security challenges for reputation mechanisms using online social networks
Reputation mechanisms are a key component of e-commerce, particularly for peer-to-peer transactions. The ratings provided by previous users can help people identify others who are likely to be reliable and encourage honest behavior among participants. ...
Mixed-initiative security agents
Security decision-making is hard for both humans and machines. This is because security decisions are context-dependent, require highly dynamic, specialized knowledge,and require complex risk analysis. Multiple user studies show that humans have ...
Keep your friends close: the necessity for updating an anomaly sensor with legitimate environment changes
Large-scale distributed systems have dense, complex code-bases that are assumed to perform multiple and inter-dependent tasks while user interaction is present. The way users interact with systems can differ and evolve over time, as can the systems ...
Active learning for network intrusion detection
Anomaly detection for network intrusion detection is usually considered an unsupervised task. Prominent techniques, such as one-class support vector machines, learn a hypersphere enclosing network data, mapped to a vector space, such that points outside ...
Using spatio-temporal information in API calls with machine learning algorithms for malware detection
Run-time monitoring of program execution behavior is widely used to discriminate between benign and malicious processes running on an end-host. Towards this end, most of the existing run-time intrusion or malware detection techniques utilize information ...
- Proceedings of the 2nd ACM workshop on Security and artificial intelligence