Saif Eddin Jabari

Saif Eddin Jabari

Auto-generated profile, based on publicly available information

Saif Eddin Jabari

New York University Abu Dhabi Abu Dhabi UAE

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
20 September 2021 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YWYue Wang
Yue Wang
ESEsha Sarkar
Esha Sarkar
WLWenqing Li
Wenqing Li
MMMichail Maniatakos
Michail Maniatakos
SJSaif Eddin Jabari
Saif Eddin Jabari
Recent work has shown that the introduction of autonomous vehicles (AVs) in traffic could help reduce traffic jams. Deep reinforcement learning methods demonstrate good performance in complex control problems, including autonomous vehicle control, and have been used in state-of-the-art AV controllers. However, deep neural networks (DNNs) render automated driving vulnerable to machine learning-based attacks. In this work, we explore the backdooring/trojanning of DRL-based AV controllers. We develop a trigger design methodology that is based on well-established principles of traffic physics. The malicious actions include vehicle deceleration and acceleration to cause stop-and-go traffic waves to emerge (congestion attacks) or AV acceleration resulting in the AV crashing into the vehicle in front (insurance attack). We test our attack on single-lane and two-lane circuits. Our experimental results show that the backdoored model does not compromise normal operation performance, with the maximum decrease in cumulative rewards being 1%. Still, it can be maliciously activated to cause a crash or congestion when the corresponding triggers appear.

23 March 2022 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Open access
BTBilal Thonnam Thodi
Bilal Thonnam Thodi
ZKZaid Saeed Khan
Zaid Saeed Khan
SJSaif Eddin Jabari
Saif Eddin Jabari
Monica MenendezMonica Menendez
Monica Menendez
We propose a kinematic wave-based Deep Convolutional Neural Network (Deep CNN) to estimate high-resolution traffic speed fields from sparse probe vehicle trajectories. We introduce two key approaches that allow us to incorporate kinematic wave theory principles to improve the robustness of existing learning-based estimation methods. First, we propose an anisotropic traffic kernel for the Deep CNN. The anisotropic kernel explicitly accounts for space-time correlations in macroscopic traffic and effectively reduces the number of trainable parameters in the Deep CNN model. Second, we propose to use simulated data for training the Deep CNN. Using a targeted simulated data for training provides an implicit way to impose desirable traffic physical features on the learning model. In the experiments, we highlight the benefits of using anisotropic kernels and evaluate the transferability of the trained model to real-world traffic using the Next Generation Simulation (NGSIM) and the German Highway Drone (HighD) datasets. The results demonstrate that anisotropic kernels significantly reduce model complexity and model over-fitting, and improve the physical correctness of the estimated speed fields. We find that model complexity scales linearly with problem size for anisotropic kernels compared to quadratic scaling for isotropic kernels. Furthermore, evaluation on real-world datasets shows acceptable performance, which establishes that simulation-based training is a viable surrogate to learning from real-world data. Finally, a comparison with standard estimation techniques shows the superior estimation accuracy of the proposed method.

1 September 2016 in Transportation Research Part B: Methodological
Verified
Journal Article
Closed access
SJSaif Eddin Jabari
Saif Eddin Jabari

3 June 2020 in IEEE Access
Verified
Journal Article
Open access
OBOuafa Benkraouda
Ouafa Benkraouda
BTBilal Thonnam Thodi
Bilal Thonnam Thodi
HYHwasoo Yeo
Hwasoo Yeo
Monica MenendezMonica Menendez
Monica Menendez
SJSaif Eddin Jabari
Saif Eddin Jabari
We propose a statistical learning-based traffic speed estimation method that uses sparse vehicle trajectory information. Using a convolutional encoder-decoder based architecture, we show that a well trained neural network can learn spatio-temporal traffic speed dynamics from time-space diagrams. We demonstrate this for a homogeneous road section using simulated vehicle trajectories and then validate it using real-world data from the Next Generation Simulation (NGSIM) program. Our results show that with probe vehicle penetration levels as low as 5%, the proposed estimation method can provide a sound reconstruction of macroscopic traffic speeds and reproduce realistic shockwave patterns, implying applicability in a variety of traffic conditions. We further discuss the model's reconstruction mechanisms and confirm its ability to differentiate various traffic behaviors such as congested and free-flow traffic states, transition dynamics, and shockwave propagation. We also provide a comparison against a widely used adaptive smoothing technique used for the same purpose and demonstrate the superiority of the proposed approach, even with probe vehicle lower penetration levels.

1 May 2022 in Transportation Science
Verified
Journal Article
Closed access
TPTheodoros P. Pantelidis
Theodoros P. Pantelidis
LLLi Li
Li Li
Tai-Yu MaTai-Yu Ma
Tai-Yu Ma
JCJoseph Y. J. Chow
Joseph Y. J. Chow
SJSaif Eddin G. Jabari
Saif Eddin G. Jabari
Viability of electric car-sharing operations depends on rebalancing algorithms. Earlier methods in the literature suggest a trend toward nonmyopic algorithms using queueing principles. We propose a new rebalancing policy using cost function approximation. The cost function is modeled as a p-median relocation problem with minimum cost flow conservation and path-based charging station capacities on a static node-charge graph structure. The cost function is NP complete, so a heuristic is proposed that ensures feasible solutions that can be solved in an online system. The algorithm is validated in a case study of electric carshare in Brooklyn, New York, with demand data shared from BMW ReachNow operations in September 2017 (262 vehicle fleet, 231 pickups per day, and 303 traffic analysis zones) and charging station location data (18 charging stations with four-port capacities). The proposed nonmyopic rebalancing heuristic reduces the cost increase compared with myopic rebalancing by 38%. Other managerial insights are further discussed.

6 February 2024 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
BTBilal Thonnam Thodi
Bilal Thonnam Thodi
SASai Venkata Ramana Ambadipudi
Sai Venkata Ramana Ambadipudi
SJSaif Eddin Jabari
Saif Eddin Jabari