International Business Machines Corporation

Volker Vogeley

Matthias Seul

Johannes Noll

Gideon Zenz

Markus Ludwig

Marc Noske

Mark Usher

Dirk Harz

Artemiy Aleksandrovich Solyakov

Astrid Granacher

Dominik W Brugger

Matthias Bartelt

Uwe Küllmar

Ashkan Vila

Marc-André Isenberg

Embodiments are disclosed for a method for identifying network risk. The method includes determining that a computing device has created a new connection to a network. Additionally, the method includes determining the public internet protocol (public IP) address of the exit point used by the network. Further, the method includes determining a reputation rating of the network based on the public IP address of the exit point. The method also includes providing a notification indicating the reputation rating of the network.

Identifying network risk

A network-accessible cyber-threat security analytics service is configured to receive and respond to requests that originate as name queries to a Domain Name System (DNS) service. Threat intelligence information provided by the service is organized into threat intelligence zones that correspond to zones exposed via the DNS service. Upon receipt of a DNS query, the query having been generated by an application seeking access to threat intelligence data exposed by the service, the query is translated into a DNS zone-specific API request based on the type of threat intelligence information sought. The zone-specific API request is then used to retrieve the requested threat intelligence information from a threat intelligence database. The requested threat intelligence information is then returned to the application by being encoded as part of a response to the DNS query. In this manner, the DNS protocol is leverage to facilitate highly-efficient access and retrieval of threat intelligence information.

Threat intelligence information access via a DNS protocol

Mechanisms are provided to implement a malicious activity response system (MARS) that automatically identifies and handles malicious activities within the data processing system. The MARS identifies threat intelligence associated with characteristics of malicious activity. The MARS forms a hypothesis for the malicious attack to identify a malicious attack that is occurring. The MARS identifies a trap for use in isolating the malicious activity; deploys the trap and automatically reconfiguring a network associated with the data processing system such that the malicious activity is routed to the trap thereby isolating the malicious activity, observes a behavior of the malicious activity within the trap; and extracts features associated with the malicious activity in the trap. The MARS then utilizes the extracted features to improve an operation of the malicious activity response system in handling future malicious activity.

Cognitive malicious activity identification and handling

A method for classification of suspicious activities is provided. In the method, a first intrusion detection system comprising a normal operation mode and which is connected to a second intrusion detection system by a first communications connection is implemented. In response to detecting a malfunction of the first communications connection, the first intrusion detection system is switched from the normal operation mode to a limited operation mode for receiving first data from one or more honeypot systems and second data from the second intrusion detection system. A prediction model for representing malicious attacks is generated by execution of a predefined classification algorithm with respect to the received data, wherein the predefined classification algorithm further determine a model evaluation metric with respect to the prediction model. The prediction model is deployed to detect the malicious attacks if the model evaluation metric meets a predefined validation condition.

Intrusion detection system

A mechanism is provided for blocking IP connection addresses and prefixes. Header information is extracted from an incoming connection request. A determination is made as to whether a portion of an Internet Protocol address comprised in the header information is blacklisted. Responsive to a portion of the Internet Protocol address being blacklisted, a fingerprint is generated, and a determination is made as to whether the fingerprint is blacklisted. Responsive to the fingerprint being blacklisted, the underlying physical connection is dropped; data associated with the incoming connection request is stored in a buffer, the fingerprint is associated to the incoming connection request; the incoming connection request is merged with stored blacklisted requests of a related originating system; and shared prefixes of the Internet Protocol address of the stored blacklisted requests are filtered out.

Creating a multi-dimensional host fingerprint for optimizing reputation for IPV6

One or more processors generate a website mimicking a virtual message board. One or more processors receive a request message directed to the website. One or more processors analyze the request message for evidence that the request message originates from a source of spam. In response to a determination that the request message likely does originate from a spam source, one or more processors provide data about the spam source to an anti-spam system.

Growing community of inventors

Bad Sooden-Allendorf, Germany

Volker Vogeley