Alina Oprea
@AlinaMOprea
Followers
2K
Following
207
Media
5
Statuses
76
Security researcher and CS professor at @Northeastern @KhouryCollege. Interested in ML security and privacy, applications of ML to security, and cloud security.
Boston, MA
Joined February 2016
I am honored to receive this award, thank you so much @Cylab for this recognition! Looking forward to visiting for the Cylab Partners Conference.
Prof. @AlinaMOprea, professor in the @KhouryCollege at @Northeastern, has been named @CyLab's 2024 Distinguished Alumni Award recipient. Learn more: https://t.co/fFrHFfa8vQ
7
0
45
You are invited to submit nominations for the 2024 Caspar Bowden Award for Outstanding Research in Privacy Enhancing Technologies! Any paper that has appeared in any peer reviewed venue between April 1, 2022 and March 31, 2024 is eligible. 1/2
1
22
21
Together with @AlinaMOprea we invite nominations for the 2024 Caspar Bowden Award for Outstanding Research in Privacy Enhancing Technologies! @PET_Symposium Please nominate your favorite privacy papers from the past 2 years by **May 10** Info and rules: https://t.co/YavYMsJXpv
0
13
33
I am on sabbatical at Google this academic year. @KairouzPeter and I are looking for a PhD student researcher this Spring / Summer to work on privacy attacks in large language models. If interested, please contact me directly by email and send your CV.
0
7
42
Congratulations to my PhD student Talha Ongun for his successful thesis defense today!
0
1
29
I am really excited about our report on adversarial ML taxonomy and terminology being published today! Joint work with @ApostolVassilev from @NIST. https://t.co/1ADZ21L8UG
csrc.nist.gov
This NIST AI report develops a taxonomy of concepts and defines terminology in the field of adversarial machine learning (AML). The taxonomy is built on survey of the AML literature and is arranged...
0
3
32
Our new paper "Network-Level Adversaries in Federated Learning", just presented at #IEEE #CNS 2022, is on arXiv: https://t.co/JZYcaeMC4V! This is a collaboration with Matthew Jagielski, @YarGokberk , Yuxuan Wang, @AlinaMOprea and @cnitarotaru
arxiv.org
Federated learning is a popular strategy for training models on distributed, sensitive data, while preserving data privacy. Prior work identified a range of security threats on federated learning...
1
5
18
All-star Guest Editors @NathalieBaraca1 and @AlinaMOprea discuss trustworthy machine learning and highlight papers from this issue of Security & Privacy Magazine https://t.co/FlEqswR9fy
@ComputerSociety
#IEEECS
0
2
5
The program of DLS 2022 @IEEESSP is finally out! @surrealyz and I can't wait to welcome you all on May 26 with a lineup of exciting research talks, including keynotes by @AlinaMOprea and @moyix and thought-provoking S&P panels (yes, S!) Curious? Head to
0
10
17
yes, we did it again - but this time it's a dedicated survey on poisoning attacks & defenses. Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning https://t.co/23RQE9NqCN with @cinofix @KathrinGrosse @ambrademontis @AlinaMOprea et al.
arxiv.org
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones,...
2
21
47
Postdoc position available! 🙂 Prof. David Wagner @Berkeley_EECS is looking for a strong postdoc with interests in applications of machine learning to security or in adversarial machine learning, starting in 2022 or early 2023. If interested, please contact daw@cs.berkeley.edu
3
32
129
In the Fall, I taught a special topics course on ML security and privacy #MLSecurity #MLPrivacy #AdversarialML. Thanks to an amazing class, we had in-depth presentations and interactive discussions on 35 papers! Check out the lecture notes and slides at:
0
31
151
Submit your best papers on adversarial ML to the Special Issue on ML Security and Privacy at the IEEE S&P Magazine @securityprivacy. Call for papers at:
computer.org
This special issue will explore emerging security and privacy issues related to machine learning and artificial intelligence techniques.
0
21
53
* ACM CCS 2021 (@acm_ccs) Free registration for students in US Institutions NSF supports free registration for students in US institutions to attend ACM CCS. Check details here:
2
15
48
First PhD hooding ceremony as an advisor! Congratulations, Matthew, and good luck at Google Brain!
10
0
278
Check out our talk, given by Giorgio Severi (@cloned_tweets), during the very first Machine Learning session today at #usesec21! Paper and slides are available to the public at the link below. Experimental code can be found here: https://t.co/nlBXxSMvzy TL;DR in this thread...
github.com
Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers - ClonedOne/MalwareBackdoors
1
5
12
Congratulations to my first PhD student Matthew Jagielski, who successfully defended his PhD thesis today! Thesis title: "Integrity and Privacy in Adversarial Machine Learning". Many thanks to the entire committee: @cnitarotaru (co-advisor), @thejonullman, and Nicholas Carlini.
8
15
168
CFP for IEEE Euro S&P 2022 is out: https://t.co/F1w6mqrCdS Papers due 22 Sept 2021. Conference in Genoa, Italy, 6-10 June 2022.
0
24
53
Postdoc positions available at @Northeastern's Experential AI Institute. Areas of interest: AI applied to cybersecurity, life sciences, healthcare informatics, information retrieval, and responsible/ethical AI. Apply at:
0
9
23
The opening remarks for #SP21 are now on YouTube. They include a welcome by the General Chair, a summary of the review process and best paper awards by the PC Chairs, the Test of Time Awards, and the IEEE Innovation in Societal Infrastructure Award. https://t.co/R1aATnnzUh
0
3
10