Bita Darvish Rouhani

Bita Darvish Rouhani

Auto-generated profile, based on publicly available information

Bita Darvish Rouhani

University of California San Diego

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
17 June 2023
Verified
Conference Paper
Open access
BRBita Darvish Rouhani
Bita Darvish Rouhani
RZRitchie Zhao
Ritchie Zhao
VEVenmugil Elango
Venmugil Elango
RSRasoul Shafipour
Rasoul Shafipour
MHMathew Hall
Mathew Hall
MNMaxim Naumov
Maxim Naumov
This paper introduces Block Data Representations (BDR), a framework for exploring and evaluating a wide spectrum of narrow-precision formats for deep learning. It enables comparison of popular quantization standards, and through BDR, new formats based on shared microexponents (MX) are identified, which outperform other state-of-the-art quantization approaches, including narrow-precision floating-point and block floating-point. MX utilizes multiple levels of quantization scaling with ultra-fine scaling factors based on shared microexponents in the hardware. The effectiveness of MX is demonstrated on real-world models including large-scale generative pretraining and inferencing, and production-scale recommendation systems.

24 September 2019 in IEEE Security & Privacy
Verified
Journal Article
Closed access
MRMohammad Sadegh Riazi
Mohammad Sadegh Riazi
BRBita Darvish Rouani
Bita Darvish Rouani
FKFarinaz Koushanfar
Farinaz Koushanfar

30 September 2018 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
BRBita Darvish Rouhani
Bita Darvish Rouhani
SHSiam Umar Hussain
Siam Umar Hussain
KLKristin Lauter
Kristin Lauter
FKFarinaz Koushanfar
Farinaz Koushanfar
Artificial Intelligence (AI) is increasingly incorporated into the cloud business in order to improve the functionality (e.g., accuracy) of the service. The adoption of AI as a cloud service raises serious privacy concerns in applications where the risk of data leakage is not acceptable. Examples of such applications include scenarios where clients hold potentially sensitive private information such as medical records, financial data, and/or location. This article proposes ReDCrypt, the first reconfigurable hardware-accelerated framework that empowers privacy-preserving inference of deep learning models in cloud servers. ReDCrypt is well-suited for streaming (a.k.a., real-time AI) settings where clients need to dynamically analyze their data as it is collected over time without having to queue the samples to meet a certain batch size. Unlike prior work, ReDCrypt neither requires to change how AI models are trained nor relies on two non-colluding servers to perform. The privacy-preserving computation in ReDCrypt is executed using Yao’s Garbled Circuit (GC) protocol. We break down the deep learning inference task into two phases: (i) privacy-insensitive (local) computation, and (ii) privacy-sensitive (interactive) computation. We devise a high-throughput and power-efficient implementation of GC protocol on FPGA for the privacy-sensitive phase. ReDCrypt’s accompanying API provides support for seamless integration of ReDCrypt into any deep learning framework. Proof-of-concept evaluations for different DL applications demonstrate up to 57-fold higher throughput per core compared to the best prior solution with no drop in the accuracy.

20 July 2025
Verified
Conference Paper
Open access
MAMengting Ai
Mengting Ai
TWTianxin Wei
Tianxin Wei
YCYifan Chen
Yifan Chen
ZZZhichen Zeng
Zhichen Zeng
RZRitchie Zhao
Ritchie Zhao
JHJingrui He
Jingrui He

18 June 2017
Verified
Conference Paper
Open access
BRBita Darvish Rouhani
Bita Darvish Rouhani
AMAzalia Mirhoseini
Azalia Mirhoseini
FKFarinaz Koushanfar
Farinaz Koushanfar
This paper proposes Deep3 an automated platform-aware Deep Learning (DL) framework that brings orders of magnitude performance improvement to DL training and execution. Deep3 is the first to simultaneously leverage three levels of parallelism for performing DL: data, network, and hardware. It uses platform profiling to abstract physical characterizations of the target platform. The core of Deep3 is a new extensible methodology that enables incorporation of platform characteristics into the higher-level data and neural network transformation. We provide accompanying libraries to ensure automated customization and adaptation to different datasets and platforms. Proof-of-concept evaluations demonstrate 10-100 fold physical performance improvement compared to the state-of-the-art DL frameworks, e.g., TensorFlow.

15 September 2020 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
MJMojan Javaheripi
Mojan Javaheripi
MSMohammad Samragh
Mohammad Samragh
BRBita Darvish Rouhani
Bita Darvish Rouhani
TJTara Javidi
Tara Javidi
FKFarinaz Koushanfar
Farinaz Koushanfar
Recent advances in adversarial Deep Learning (DL) have opened up a new, largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. This paper introduces CuRTAIL, a novel end-to-end framework to characterize and thwart adversarial attacks and significantly improve the reliability (safety) of a victim model. We formalize the goal of preventing adversarial attacks as an optimization problem to minimize the rarely observed regions in the latent feature space spanned by a DL network. To solve the aforementioned minimization problem, a set of complementary but disjoint modular redundancies are trained to validate the legitimacy of the input samples. The proposed countermeasure is unsupervised, meaning that no adversarial sample is leveraged to train modular redundancies. This, in turn, ensures the effectiveness of the defense in the face of generic attacks. We evaluate the robustness of our proposed methodology against the state-of-the-art adaptive attacks in a white-box setting considering that the adversary knows everything about the victim model and its defenders. Extensive evaluations for analyzing MNIST, CIFAR10, and ImageNet corroborate the effectiveness of CuRTAIL against adversaries. Modular redundancy computations can be performed independently. Thus, CuRTAIL detection algorithm can be distributed among multiple hardware settings to achieve maximum throughput.