Home > News > All News > Atul Prakash

Atul Prakash

Eleven papers by CSE researchers at ICLR 2025

CSE authors are presenting new research on topics related to deep learning, including spatial reasoning in vision-language models, data selection methods, and moral alignment in language models.

Seventeen papers by CSE researchers at NeurIPS 2024

Papers by CSE authors cover a variety of topics related to machine learning and neural information processing.

Atul Prakash named chair of Computer Science and Engineering

Prakash is an expert in the security and privacy of computer systems.

Four papers by CSE researchers appearing at CCS 2023

CSE-authored papers at the conference cover cutting-edge topics related to computer security.

Five papers by CSE researchers presented at ICML 2023

The papers authored by CSE researchers appearing at the conference cover a breadth of topics related to machine learning.

The same app can pose a bigger security and privacy threat depending on the country where you download it, study finds

Same app, same app store, different risks if you download it in, say, Tunisia rather than in Germany.

Three CSE grad students recognized by NSF Graduate Research Fellowship Program

This program recognizes and supports outstanding graduate students.

CSE researchers report over $11M in research grants last quarter

The awards were distributed to 18 different primary investigators.

Three faculty earn MIDAS grants to broaden the frontiers of data science

This round of funding strongly encourages pioneering work with the potential for major expansion.

Tyche: A new permission model to defend against smart home hacks

“The work is an important step towards understanding how to make tradeoffs between usability and security.”

2017 EECS Outstanding Achievement Awards

Congratulations!

Several Michigan Papers Presented at 2016 USENIX Security Symposium

A total of five papers authored by CSE researchers were presented.

Two Michigan papers win top awards at IEEE Security and Privacy Symposium

One of the paper describes and demonstrates a malicious hardware backdoor. The other demonstrated security failings in a commercial smart home platform.

Hacking into homes: Security flaws found in SmartThings connected home system

New vulnerabilities form when hardware like electronic locks, thermostats, ovens, sprinklers, lights and motion sensors are networked and set up to be controlled remotely.

Computer scientists funded for new inquiry into non-consumptive research

Smart bridges under development with new grant

The monitoring system will collect data from surface and penetrating sensors, then wirelessly relay the information to an inspector on site or miles away.