Jung-Woo Chang

Ph.D. Candidate
juc023 [at] ucsd [dot] edu
Electrical and Computer Engineering
UC San Diego
Google Scholar Google Scholar
Linkedin logo LinkedIn
CV Icon CV

I'm a Ph.D. Candidate in UC San Diego, under the supervision of Prof. Farinaz Koushanfar. I also had the privilege of closely working with Prof. Xinyu Zhang and Prof. Prof. Ke Sun.

Research Interests
  • Wireless and Network Security
  • AI Security
  • Cyber-Physical Systems
  • Sensor Privacy
  • Robust Neural Video Codecs
  • Hardware Acceleration

News

  • Mar 2025, EveGuard is accepted to S&P'25.
  • Jan 2025, Excited to receive the NDSS Fellowship!
  • Nov 2024, Excited to be accepted to attend the NSF NeTS Early Career Investigator Workshop!
  • Oct 2024, Glad to be invited as a AEC member of Usenix Security 2025!
  • Oct 2024, Passed my Ph.D. Proposal. Now a Ph.D. Candidate!

Education

  • Sep. 2021 ~ Jul. 2025, UC San Diego, Ph.D. in Electrical and Computer Engineering (Advisor: Prof. Farinaz Koushanfar)
  • Mar. 2017 ~ Feb. 2019, Sogang University, MS. in Electronic Engineering (Advisor: Prof. Suk-Ju Kang)
  • Mar. 2010 ~ Feb. 2016, Sogang University, BS in Electronic Engineering (Served in Korea Air Force for 2 years)

Conference

  1. Jung-Woo Chang and Suk-Ju Kang. 2018. Optimizing FPGA-based convolutional neural networks accelerator for image super-resolution, IEEE/ACM Asia and South Pacific Design Automation Conference (ASP-DAC).

  2. Jung-Woo Chang, Keon-Woo Kang, and Suk-Ju Kang. 2019. SDCNN: An efficient sparse deconvolutional neural network accelerator on FPGA. IEEE/ACM Design Automation and Test in Europe (DATE).

  3. Jung-Woo Chang*, Saehyun Ahn*, Keon-Woo Kang, and Suk-Ju Kang. 2020. Towards Design Methodology of Efficient Fast Algorithms for Accelerating Generative Adversarial Networks on FPGAs. IEEE/ACM Asia and South Pacific Design Automation Conference (ASP-DAC).

  4. Saehyun Ahn, Jung-Woo Chang, and Suk-Ju Kang. 2020. An Efficient Accelerator Design Methodology for Deformable Convolutional Networks. IEEE international conference on image processing (ICIP).

  5. Jung-Woo Chang, Mojan Javaheripi, and Farinaz Koushanfar. 2023. RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression. Network and Distributed System Security (NDSS) Symposium (Acceptance ratio: 58/398=14.6%).

  6. Jung-Woo Chang, Mojan Javaheripi, and Farinaz Koushanfar. 2023. VideoFlip: Adversarial Bit-Flips for Reducing Video Service Quality. ACM/IEEE Design Automation Conference (DAC) (Acceptance ratio: 22.7%).

  7. Jung-Woo Chang, Ke Sun, Nasimeh Heydaribeni, Seira Hidano, Xinyu Zhang, and Farinaz Koushanfar. 2025. Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems. Network and Distributed System Security (NDSS) Symposium (Acceptance ratio: 16.1%).

  8. Jung-Woo Chang, Ke Sun, Xinyu Zhang, and Farinaz Koushanfar. 2025. EveGuard: Defeating Vibration-based Side-Channel Eavesdropping with Audio Adversarial Perturbations. IEEE Symposium on Security and Privacy (S&P) (Acceptance ratio: 14.9%).

Journal

  1. Jung-Woo Chang, Keon-Woo Kang, and Suk-Ju Kang. 2020. An Energy-Efficient FPGA-based Deconvolutional Neural Networks Architecture for Single Image Super-Resolution. IEEE Transactions on Circuits and Systems for Video Technology.

  2. Mojan Javaheripi, Jung-Woo Chang, and Farinaz Koushanfar. 2022. AccHashtag: Accelerated Hashing for Detecting Fault-Injection Attacks on Embedded Neural Networks. ACM Journal on Emerging Technologies in Computing Systems.

  3. Saehyun Ahn*, Jung-Woo Chang*, Hyeon-Seok Yoon, and Suk-Ju Kang. 2022. TouchNAS: Efficient Touch Detection Model Design Methodology for Resource-Constrained Devices. IEEE Sensors Journal.

Under Submission

  1. Jung-Woo Chang, Ke Sun, Xinyu Zhang, and Farinaz Koushanfar. 2025. Nocturne: Compromising Integrity of Video Streaming via Universal Bit Flips on Neural Video Codecs. Submitted to top security conference.

Selected Projects

Protecting Speech Privacy from Sensor-based Eavesdropping [C8], 2024 - 2025
Robotic sensors pose significant privacy risks by allowing eavesdroppers to sense vibrations from sound sources or nearby objects. I built the first software-driven defense framework that leverages the unique features of eavesdropping devices to protect sensitive speech information.

Physical-Layer Wireless Security for NextG Systems [C7], 2023 - 2024
NextG wireless networks are promised to leverage ML techniques to deliver ultra-reliable, low-latency communication. However, the practical vulnerabilities of NextG wireless networks remain unexplored. I developed a novel wireless attack methodology that generates practically feasible adversarial signals to target any multimodal signal transmitted over a wireless channel.

Hardware Fault Injection on Video Systems [C6, O1], 2022 - 2025
I demonstrate the first hardware-based attack on video streaming that deterministically induces bit flips in ML parameters to degrade user experience by exploiting the Rowhammer vulnerability. Furthermore, I devised a practically feasible BFA methodology that understands system constraints and minimizes the number of bit flips.

Real-Time Adversarial Attacks on Video Systems [C5], 2021 - 2022
I present the first systematic framework for adversarial attacks targeting neural video codecs and downstream classification systems. My analysis reveals that an attacker can manipulate the Rate-Distortion (R-D) relationship in video compression models, leading to denial-of-service in real-time.

Industrial Experience

  • Jul. 2024 ~ Sep. 2024, NXP Semiconductors, Wireless Research Intern
  • Jun. 2022 ~ Sep. 2022, Chainlink Labs, Research Intern
  • Jan. 2019 ~ Aug. 2021, LG Uplus, Research Engineer

Academic Activities

  • Internet Society NDSS Fellowship, 2025
  • NeTS Early Career Investigator Workshop Travel Grant, 2025
  • DAC Richard Newton Young Student Fellowship, 2022
  • Electrical and Computer Engineering Department Fellowship, UC San Diego, 2021
  • Samsung Electronics Semiconductor Best Paper Award from Samsung Electronics, 2021
  • Qualcomm Best Paper Award(Excellence award) from Qualcomm Korea and Sogang University, 2018
  • Industry-Academia Scholarship Recipient from LG, 2018
  • Young Leaders Award(Bronze Prize) from The 18th International Meeting on Information Display (IMID), 2018

Paper Review and Program Committee Experiences

  • Artifact Evaluation Committee, USENIX Security, 2025
  • Reviewer in Proceedings of the IEEE
  • Reviewer in ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec)
  • Reviewer in ACM The Annual International Conference on Mobile Computing and Networking (MobiCom)
  • Reviewer in IEEE/EDAC/ACM Design Automation Conference (DAC)
  • Reviewer in IEEE Transactions on Circuits and Systems I: Regular Papers (TCAS-I)
  • Reviewer in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Reviewer in ACM Transactions on Multimedia Computing, Communications, and Applications
  • Reviewer in Journal of Systems Architecture

Teaching Assistant

  • University of California San Diego, Optimization and Acceleration of Deep Learning on Various Hardware Platforms, 2023 Spring
  • Sogang University, Automatic Control Systems, 2017 Spring
  • Sogang University, Microprocessor-Based System Design, 2017 Fall