I'm an Assistant Professor at the University of California, San Diego in the Computer Science and Engineering department. My goal is to enable society to gain the benefits of emerging technologies without the security and privacy risks. I have received two best paper awards (at IEEE S&P and IEEE SecDev), the NSF CAREER award, and research awards from Facebook, Amazon and Google. My work has been featured in Wired, The Verge, Ars Technica, Science Magazine and Nature. It is also on display at the Science Museum in London (One of the experimental artifacts is now part of the Science Museum's permanent collection). I earned my Ph.D. in Computer Science and Engineering at the University of Michigan in 2017 where I was advised by Prof. Atul Prakash. Before coming to UC San Diego, I spent three excellent years at the University of Wisconsin-Madison.
Selected publications
-
Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
Andrey Labunets, Nishit Pandya, Ashish Hooda, Xiaohan Fu, Earlence Fernandes
46th IEEE Symposium on Security and Privacy, San Francisco, CA, May 2025.
Impact and OutreachWebsite with demos, Ars Technica, Android Authority -
Imprompter: Tricking LLM Agents into Improper Tool Use
Xiaohan Fu, Shuheng Li, Zihan Wang, Yihao Liu, Rajesh K. Gupta, Taylor Berg-Kirkpatrick, Earlence Fernandes
arXiv preprint 2410.14923, Oct 2024.
Impact and Outreach Website with demos, WIRED, IEEE Spectrum, Simon Willison's Blog, Mistral's Fix Confirmation (see Sep 13, 2024 entry) -
Stateful Least Privilege Authorization for the Cloud
Leo Cao, Luoxi Meng, Deian Stefan, Earlence Fernandes
33rd USENIX Security Symposium, Philadelphia, PA, Aug 2024 -
MakeShift: Security Analysis of Shimano Di2 Wireless Gear Shifting in Bicycles
Maryam Motallebighomi, Earlence Fernandes, Aanjhan Ranganathan.
USENIX WOOT Conference on Offensive Technologies (WOOT), Philadelphia, PA, Aug 2024
Impact and Outreach WIRED, Escape Collective, The Verge, Schneier on Security, Gizmodo, GCN, Ars Technica, Jalopnik, Road.cc, Cycling Weekly, Cycling News, IT Brew, Kaspersky, Forbes, Shane Miller - GPLama - On the Difficulty of updating the shifters, HackRF User Reproduced the Attack, KPBS TV Interview -
Robust Physical-World Attacks on Deep Learning Visual Classification
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash,Tadayoshi Kohno, Dawn Song
Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, UT (supersedes arXiv:1707.08945), June 2018
Acceptance Rate: 29.6%
Impact and Outreach IEEE Spectrum, Yahoo News, Wired, Engagdet, Telegraph, Car and Driver, CNET, Digital Trends, SCMagazine, Schneier on Security, Ars Technica, Fortune, Science Magazine, Nature -
Security Analysis of Emerging Smart Home Applications Distinguished Practical Paper Award
Earlence Fernandes, Jaeyeon Jung, Atul Prakash
37th IEEE Symposium on Security and Privacy (S&P 2016), San Jose, May 2016
Acceptance Rate: 13.3%
Impact and Outreach WIRED, Schneier on Security, The Verge, Gizmodo, Ars Technica, CNET, Mashable, Detroit Free Press, ...
Students
- Andrey Labunets (current, PhD)
- Luoxi Meng (current, PhD)
- Nishit Pandya (current, PhD)
- Xiaohan Fu (co-advised w/ Rajesh Gupta, PhD)
- Leo Cao (MS 2024) -> PhD Student at UW Madison
- Yunang Chen (PhD 2023) -> Google
- Ashish Hooda (MS 2021) -> PhD student at UW Madison
- Luna Sayles (MS 2021)
- Jon Sharp (MS 2020) -> Amazon
- Tyler Gu (BS 2021) -> PhD student at UIUC
- Ruizhe Wang (BS 2021) -> PhD student at Univ. of Waterloo
Awards
-
Google Research Scholar Award
2024
-
Amazon Research Award
2022
-
NSF CAREER
2022
-
Facebook Research Award
2021
-
IEEE SecDev Best Research Paper Award
2018
-
IEEE S&P Distinguished Practical Paper Award
2016
Books
-
Instant Android Systems Development
Earlence Fernandes
Packt Publishers
UK, 2013