ICSI hosts basic, pre-competitive research of fundamental importance to computer science and engineering. Projects are chosen based on the interests of the Institute’s principal investigators and the strengths of its researchers and affiliated UC Berkeley faculty.

Recent projects are listed below; the full list of each group's projects is accessible via the links listed in the sidebar.

Multi Modal Video Summarization

ICSI researchers have been working with DAC to identify and acquire datasets that are sufficient for training Automated Speech Recognition (ASR) models. They are researching and developing ASR models that are robust to noise, music, babble and reverberation. This may include, but is not limited to, the research and implementation of signal processing algorithms that remove segments of an audio stream that do not include speech.

Audio and Multimedia
Identifying semantic components

Identifying potential WMD-related threats before they materialize requires the ability to discover and analyze low-observable WMD-related information from data of all types, including social media. To help build the robust natural language understanding (NLU) systems needed for this goal, this project investigates the automatic identification of semantic components, sub-lexical elements of linguistic meaning that may be composed in different ways to capture the meanings of words.

Multilingual FrameNet: Merging FrameNets for Cross-linguistic Research

One of the greatest challenges to NLP is the increasing variety of languages on the internet; part of the answer to this challenge can come from the FrameNet lexical database, which has been developed for English since 1997 at the International Computer Science Institute (ICSI) based on the principles of Frame Semantics (Fillmore 1977; Fillmore 1985). The lexicon is organized by semantic frames, with valence information derived from attested, manually annotated corpus examples (Fillmore & Baker 2010).

PacketLab: A Universal Measurement Endpoint Interface

The right vantage point is critical to the success of any active measurement. However, most research groups cannot afford to design, deploy, and maintain their own network of measurement endpoints, and thus rely measurement infrastructure shared by others. Unfortunately, the mechanism by which we share access to measurement endpoints today is not frictionless; indeed, issues of compatibility, trust, and a lack of incentives get in the way of efficiently sharing measurement infrastructure.

Networking and Security
Rethinking Home Networking for the Ultrabroadband Era

People generally center their lives around their residence. This center of gravity is where we can be contacted, store our things, do our homework, play games, meet after disparate activities, eat our meals, and so on. Our digital lives are, however, not organized around such a hub. Rather, we use a myriad of services to communicate with one another, store pictures, work on documents, share videos, keep our music, deal with calendars, etc. In this arrangement we are the hub. Our content and information comes to us from a range of places to wherever we happen to be at the moment.

Networking and Security
Privacy Risk in Machine Learning Pipelines

ICSI researchers are working with researchers at Carnegie Mellon University on tracking private data through machine learning pipelines. They will develop stronger notions of proxy that account for why a classifier is using information by: 

Networking and Security
Previous Work: Implement and Evaluate Matrix Algorithms in Spark on High Performance Computing Platforms for Science Applications

The overall goal of this project is to enable the Berkeley Data Analytics Stack (BDAS) to run efficiently on the Cray XC30 and Cray XC40 supercomputer platforms. BDAS has a rich set of capabilities and is of interest as a computational environment for very large-scale machine learning and data analysis applications. To extend the capabilities of BDAS, ICSI researchers will consider the performance of deterministic and randomized matrix algorithms for problems such as least-squares approximation and low-rank matrix approximation that underlie many common machine-learning algorithms.

Big Data
Previous Work: Local Algorithms for Large Informatics Graphs

A serious problem with many existing machine learning and data analysis tools in the complex networks area is that they are often very brittle and/or do not scale well to larger networks. As a consequence, analysts often develop intuition on small networks, with 102 or 103 nodes, and then try to apply these methods on larger networks, with 105 or 107 or more nodes. Larger networks, however, often have very different static and dynamic properties than smaller networks.

Big Data
Liquid Data Networking

Packet loss often occurs when transmitting over wireless links, due to interference, intermittent obstacles, routing changes as conditions vary, etc. As examples, interference and the resulting packet loss are major concerns as the Internet is extended using wireless mesh networks, 5G millimeter wave transmission is known to be prone to packet loss with even the slightest obstruction, and slight variations in atmospheric conditions cause packet loss in laser communications between ground stations and drones or satellites.

Exploring the Boundaries of Passive Listening in Voice Assistants

Various forms of voice assistants—stand-alone devices or those built into smartphones—are becoming increasingly popular among consumers. Currently, these systems react when you directly speak to them using a specific wake-word, such as “Alexa,” “Siri,” “Ok Google.” However, with advancements in speech recognition, the next generation of voice assistants is expected to always listen to the acoustic environment and proactively provide services and recommendations based on human conversations or other audio signals, without being explicitly invoked.

Usable Security and Privacy
Low latency/high reliability streaming video prototype based on RaptorQ

We are happy to announce the availability of prototype software implementing low latency/high reliability video streaming based on RaptorQ.  The prototype uses the ROUTE protocol, which in turn uses RaptorQ to provide protection against packet loss. ROUTE and RaptorQ are specified in A/331, “Signaling, Delivery, Synchronization, and Error Protection”, as part of the ATSC 3.0 standard for delivery of media and non-timed data.

Intelligent Channel Management for Wireless Mesh Networks

ICSI's TCS team is working with Facebook to build and evaluate a system wide network channel management tool for a wireless mesh network. The aim of the collaboration is to increase wireless capacity, decrease interference between devices (self and external), and provide more automated and intelligent network channel management and planning.

Funding being provided by Facebook Connectivity.

Enhancements for Wireless Mesh Networks

ICSI's TCS team is working with Facebook to simulate, understand and enhance wireless mesh networks. The main goal of the effort is to build a high fidelity simulator for wireless mesh networks to understand the performance scaling of such networks and improve coverage, density, throughput. Potential enhancements include extending the reach and performance of wireless mesh networks i.e. to support more hops and/or provide superior internet connectivity, using technology which avoids deep changes to the network or wireless technology.


The RaptorQ erasure code (specified in IETF RFC 6330) enables reliable wireless communication systems, including high quality streaming and delivery of large data packages.

Under the auspices of the International Computer Science Institute, the Codornices project aims to spur further adoption and deployment of RaptorQ by developing a high performance software implementation of RaptorQ and developing application software that supports different use cases and standards that leverage RaptorQ.

Co-Design of Network, Storage and Computation Fabrics for Disaggregated Datacenters

Traditional datacenters are built using servers, each of which tightly integrates a small amount of CPU, memory and storage onto a single motherboard. The slowdown of Moore's Law has led to surfacing of several fundamental limitations of such server-centric architectures (e.g, the memory-capacity wall making CPU-memory co-location unsustainable). As a result, a new computing paradigm is emerging --- a disaggregated datacenter architecture, where each resource type is built as a standalone "blade" and a network fabric interconnects the resource blades within and across datacenter racks.

Networking and Security
Universal Packet Scheduling

This project addresses a seemingly simple question: Is there a universal packet scheduling algorithm? More precisely, researchers are analyzing whether there is a single packet scheduling algorithm that, at a network-wide level, can perfectly match the results of any given scheduling algorithm. The question of universal packet scheduling is being investigated from both a theoretical and empirical perspective.

Networking and Security
Bro Intrusion Detection System Refinements

ICSI is working with LBNL on refinements to Zeek (formerly known as Bro). The work includes troubleshooting and resolving the most complex problems with the Zeek network monitor, development/integration of the communication framework, development and implementation of new features for the Input framework, and development of a persistence solution for the NetControl and Catch-and Release frameworks of Zeek/Bro. Zeek/Bro is an open-source network intrustion detection system developed at ICSI and LBNL which is currently in use at Fortune 500 companies, universities, and governments.

Networking and Security
Multimodal Feature Learning for Understanding Consumer Produced Multimedia Data

ICSI is working with LLNL on ongoing work on feature extraction and analytic techniques that map raw data from multiple input modalities (e.g., video, images, text) into a joint semantic space. This requires cutting edge research in multiple modalities, as well as in the mathematical methods to learn the semantic mappings.

Audio and Multimedia
When do Computers Discriminate? Toward Informing Users About Algorithmic Discrimination

In this collaborative project with University of Maryland, ICSI researchers are tackling the challenge of explaining what constitutes unacceptable algorithmic discrimination. Getting the answer to this question right is key to unlocking the potential of automated decision systems without eroding the ability of people to get a fair deal and advance in society.

Networking and Security
Variable Precision Computing LDRD Project

Large-scale physics simulations pose a significant challenge on the currently available computational resources, because of the costs of both communication and storage largely exceeding the cost of the actual computation. The efficient management of the Exascale data flows generated by a large-scale simulation is still an unsolved problem. This project aims to provide an initial solution to this problem.

Research Initiatives