Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control
Нема приказа
Конференцијски прилог (Објављена верзија)
,
IEEE
Метаподаци
Приказ свих података о документуАпстракт
Visual servoing represents a control strategy
capable of driving dynamical systems from the current to the
desired pose, when the only available information is the images
generated at both poses. In this work, we analyze vulnerability
of such systems and introduce two types of attacks to deceive
visual servoing controller within a wheeled mobile robotic
system. The attack goal is to alter the visual servoing procedure
in such a way that mobile robot achieves the pose defined by an
attacker instead of the desired one. Specifically, the attacks
exploit image transformations developed using a methodology
based on simulated annealing. The main difference between the
attacks is the considered threat model – i.e., how the attacker
has infiltrated the system. The first attack assumes the realtime camera feed has been compromised and thus, the images
from the current pose are modified (e.g., during the acquisition
or communication); for the second, only the desired destination
i...mage is potentially altered. Finally, in 3D simulations and realworld experiments, we show the effectiveness of cyber-attacks.
Извор:
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023, 6342-6348Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200105 (Универзитет у Београду, Машински факултет) (RS-MESTD-inst-2020-200105)
- ONR-N00014-23-1-2206
- ONR-N00014-20-1-2745
- AFOSR-FA9550-19-1-0169
- NSF-CNS-1652544
- NSF-CNS- 2112562
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Jokić, Aleksandar AU - Khazraei, Amir AU - Petrović, Milica AU - Jakovljević, Živana AU - Pajić, Miroslav PY - 2023 UR - https://machinery.mas.bg.ac.rs/handle/123456789/7676 AB - Visual servoing represents a control strategy capable of driving dynamical systems from the current to the desired pose, when the only available information is the images generated at both poses. In this work, we analyze vulnerability of such systems and introduce two types of attacks to deceive visual servoing controller within a wheeled mobile robotic system. The attack goal is to alter the visual servoing procedure in such a way that mobile robot achieves the pose defined by an attacker instead of the desired one. Specifically, the attacks exploit image transformations developed using a methodology based on simulated annealing. The main difference between the attacks is the considered threat model – i.e., how the attacker has infiltrated the system. The first attack assumes the realtime camera feed has been compromised and thus, the images from the current pose are modified (e.g., during the acquisition or communication); for the second, only the desired destination image is potentially altered. Finally, in 3D simulations and realworld experiments, we show the effectiveness of cyber-attacks. C3 - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) T1 - Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control EP - 6348 SP - 6342 DO - 10.1109/IROS55552.2023.10341376 ER -
@conference{ author = "Jokić, Aleksandar and Khazraei, Amir and Petrović, Milica and Jakovljević, Živana and Pajić, Miroslav", year = "2023", abstract = "Visual servoing represents a control strategy capable of driving dynamical systems from the current to the desired pose, when the only available information is the images generated at both poses. In this work, we analyze vulnerability of such systems and introduce two types of attacks to deceive visual servoing controller within a wheeled mobile robotic system. The attack goal is to alter the visual servoing procedure in such a way that mobile robot achieves the pose defined by an attacker instead of the desired one. Specifically, the attacks exploit image transformations developed using a methodology based on simulated annealing. The main difference between the attacks is the considered threat model – i.e., how the attacker has infiltrated the system. The first attack assumes the realtime camera feed has been compromised and thus, the images from the current pose are modified (e.g., during the acquisition or communication); for the second, only the desired destination image is potentially altered. Finally, in 3D simulations and realworld experiments, we show the effectiveness of cyber-attacks.", journal = "2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)", title = "Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control", pages = "6348-6342", doi = "10.1109/IROS55552.2023.10341376" }
Jokić, A., Khazraei, A., Petrović, M., Jakovljević, Ž.,& Pajić, M.. (2023). Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control. in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 6342-6348. https://doi.org/10.1109/IROS55552.2023.10341376
Jokić A, Khazraei A, Petrović M, Jakovljević Ž, Pajić M. Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control. in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2023;:6342-6348. doi:10.1109/IROS55552.2023.10341376 .
Jokić, Aleksandar, Khazraei, Amir, Petrović, Milica, Jakovljević, Živana, Pajić, Miroslav, "Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control" in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2023):6342-6348, https://doi.org/10.1109/IROS55552.2023.10341376 . .