Estimating Parameters of Target's Detection Methods
| Authors | |
|---|---|
| Year of publication | 2017 |
| Type | Article in Proceedings |
| Conference | Proceedings of the NATO IST-152 Workshop on Intelligent Autonomous Agents for Cyber Defence and Resilience |
| MU Faculty or unit | |
| Citation | |
| Web | http://ceur-ws.org/Vol-2057/Paper12.pdf |
| Field | Informatics |
| Keywords | dictionary attacks; attack parameters estimation |
| Description | Dictionary attacks are a prevalent phenomenon, which was lately amplified with the onset of insecure SOHO and IoT devices. Some of these devices use their own protection against dictionary attacks and some offload their security to mechanisms deployed in the infrastructure, such as flow-based IPS systems. These mechanism often operate with the notion of a typical attacker, who represent common attacks against the infrastructure and lacks sophistication. However, the emergence of stealthy and distributed dictionary attacks indicate that detection mechanisms should take sophisticated attackers into account. In this paper we explore the capability of a sophisticated attacker, who can estimate parameters of detection methods deployed on target and can then craft an attack which could go undetected for arbitrary long time. For this, we propose a new model of attacker-target interaction during dictionary attacks, which is based on attacker's perspective. Using this model we then postulate and experimentally evaluate an algorithm for estimating parameters of target detection method, illustrating that an attacker requires only a handful of attack attempts to correctly guess these parameters. |