Ruisi Zhang

Ruisi Zhang

Auto-generated profile, based on publicly available information

Ruisi Zhang

UC San Diego, La Jolla, CA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 May 2024 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
NHNasimeh Heydaribeni
Nasimeh Heydaribeni
XZXinrui Zhan
Xinrui Zhan
RZRuisi Zhang
Ruisi Zhang
TETina Eliassi-Rad
Tina Eliassi-Rad
FKFarinaz Koushanfar
Farinaz Koushanfar

23 June 2024
Verified
Conference Paper
Open access
RZRuisi Zhang
Ruisi Zhang
FKFarinaz Koushanfar
Farinaz Koushanfar
This paper introduces EmMark, a novel watermarking framework for protecting intellectual property (IP) of embedded large language models deployed on resource-constrained edge devices. To address the IP theft risks posed by malicious end-users, EmMark enables proprietors to authenticate ownership by querying the watermarked model weights and matching the inserted signatures. EmMark's novelty lies in its strategic watermark weight parameters selection, ensuring robustness and maintaining model quality. Extensive proof-of-concept evaluations of models from OPT and LLaMA-2 families demonstrate EmMark's fidelity, achieving 100% success in watermark extraction with model performance preservation. EmMark also showcased its resilience against watermark removal and forging attacks.

26 October 2023
Verified
Conference Paper
Open access
YPYe Pan
Ye Pan
RZRuisi Zhang
Ruisi Zhang
JWJingying Wang
Jingying Wang
YDYu Ding
Yu Ding
KMKenny Mitchell
Kenny Mitchell
Our aim is to improve animation production techniques' efficiency and effectiveness. We present two real-time solutions which drive character expressions in a geometrically consistent and perceptually valid way. Our first solution combines keyframe animation techniques with machine learning models. We propose a 3D emotion transfer network makes use of a 2D human image to generate a stylized 3D rig parameter. Our second solution combines blendshape-based motion capture animation techniques with machine learning models. We propose a blendshape adaption network which generates the character rig parameter motions with geometric consistency and temporally stability. We demonstrate the effectiveness of our system by comparing it to a commercial product Faceware. Results reveal that ratings of the recognition, intensity, and attractiveness of expressions depicted for animated characters via our systems are statistically higher than Faceware. Our results may be implemented into the animation pipeline, supporting animators to create expressions more rapidly and precisely.

18 March 2025 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
RZRuisi Zhang
Ruisi Zhang
RRRachel Selina Rajarathnam
Rachel Selina Rajarathnam
DPDavid Z. Pan
David Z. Pan
FKFarinaz Koushanfar
Farinaz Koushanfar
Physical design watermarking (WM) on contemporary integrated circuit (IC) layout encodes signatures without considering the dense connections and design constraints, which could lead to performance degradation on the watermarked products. This article presents ICMarks, a quality-preserving and robust WM framework for modern IC physical design. ICMarks embeds unique watermark signatures during the physical design’s placement stage, thereby authenticating the IC layout ownership. ICMarks’s novelty lies in 1) strategically identifying a region of cells to watermark with minimal impact on the layout performance and 2) a two-level WM framework for augmented robustness toward potential removal and forging attacks. Extensive evaluations on benchmarks of different design objectives and sizes validate that ICMarks incurs no wirelength and timing metrics degradation, while successfully proving ownership. Furthermore, we demonstrate ICMarks is robust against two major WM attack categories, namely, watermark removal and forging attacks; even if the adversaries have prior knowledge of the WM schemes, the signatures cannot be removed without significantly undermining the layout quality.

16 October 2023 in ACM Transactions on Design Automation of Electronic Systems
Verified
Journal Article
Open access
RZRuisi Zhang
Ruisi Zhang
SHShehzeen Hussain
Shehzeen Hussain
HCHuili Chen
Huili Chen
MJMojan Javaheripi
Mojan Javaheripi
FKFarinaz Koushanfar
Farinaz Koushanfar
Deep learning (DL) models are enabling a significant paradigm shift in a diverse range of fields, including natural language processing and computer vision, as well as the design and automation of complex integrated circuits. While the deep models – and optimizations based on them, e.g., Deep Reinforcement Learning (RL) – demonstrate a superior performance and a great capability for automated representation learning, earlier works have revealed the vulnerability of DL to various attacks. The vulnerabilities include adversarial samples, model poisoning, and fault injection attacks. On the one hand, these security threats could divert the behavior of the DL model and lead to incorrect decisions in critical tasks. On the other hand, the susceptibility of DL to potential attacks might thwart trustworthy technology transfer as well as reliable DL deployment. In this work, we investigate the existing defense techniques to protect DL against the above-mentioned security threats. Particularly, we review end-to-end defense schemes for robust deep learning in both centralized and federated learning settings. Our comprehensive taxonomy and horizontal comparisons reveal an important fact that defense strategies developed using DL/software/hardware co-design outperform the DL/software-only counterparts and show how they can achieve very efficient and latency-optimized defenses for real-world applications. We believe our systemization of knowledge sheds light on the promising performance of hardware-software co-design of DL security methodologies and can guide the development of future defenses.

9 September 2024
Verified
Conference Paper
Open access
RZRuisi Zhang
Ruisi Zhang
RRRachel Selina Rajarathnam
Rachel Selina Rajarathnam
DPDavid Z. Pan
David Z. Pan
FKFarinaz Koushanfar
Farinaz Koushanfar
This paper presents AutoMarks, an automated and transferable watermarking framework that leverages graph neural networks to reduce the watermark search overheads during the placement stage. AutoMarks's novel automated watermark search is accomplished by (i) constructing novel graph and node features with physical, semantic, and design constraint-aware representation; (ii) designing a data-efficient sampling strategy for watermarking fidelity label collection; and (iii) leveraging a graph neural network to learn the connectivity between cells and predict the watermarking fidelity on unseen layouts. Extensive evaluations on ISPD'15 and ISPD'19 benchmarks demonstrate that our proposed automated methodology: (i) is capable of finding quality-preserving watermarks in a short time; and (ii) is transferable across various designs, i.e., AutoMarks trained on one layout is generalizable to other benchmark circuits. AutoMarks is also resilient against potential watermark removal and forging attacks.