TY - JOUR
T1 - Reliable Smart Road Signs
AU - Sayin, Muhammed O.
AU - Lin, Chung Wei
AU - Kang, Eunsuk
AU - Shiraishi, Shinichi
AU - Başar, Tamer
N1 - Manuscript received January 15, 2019; revised June 3, 2019 and September 28, 2019; accepted October 2, 2019. Date of publication October 15, 2019; date of current version November 30, 2020. This work was supported in part by the U.S. Office of Naval Research (ONR) MURI under Grant N00014-16-2710, in part by the Ministry of Education (MOE), Taiwan, under Grant NTU-107V0901 and Grant NTU-108V0901, and in part by the Ministry of Science and Technology (MOST), Taiwan, under Grant MOST-108-2636-E-002-011. The Associate Editor for this article was W. Lin. (Corresponding author: Muhammed O. Sayin.) M. O. Sayin is with the Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139 USA (e-mail: [email protected]).
PY - 2020/12
Y1 - 2020/12
N2 - In this paper, we propose a game theoretical adversarial intervention detection mechanism for reliable smart road signs. A future trend in intelligent transportation systems is 'smart road signs' that incorporate smart codes (e.g., visible at infrared) on their surface to provide more detailed information to smart vehicles. Such smart codes make road sign classification problem aligned with communication settings more than conventional classification. This enables us to integrate well-established results in communication theory, e.g., error-correction methods, into road sign classification problem. Recently, vision-based road sign classification algorithms have been shown to be vulnerable against (even) small scale adversarial interventions that are imperceptible for humans. On the other hand, smart codes constructed via error-correction methods can lead to robustness against small scale intelligent or random perturbations on them. In the recognition of smart road signs, however, humans are out of the loop since they cannot see or interpret them. Therefore, there is no equivalent concept of imperceptible perturbations in order to achieve a comparable performance with humans. Robustness against small scale perturbations would not be sufficient since the attacker can attack more aggressively without such a constraint. Under a game theoretical solution concept, we seek to ensure certain measure of guarantees against even the worst case (intelligent) attackers that can perturb the signal even at large scale. We provide a randomized detection strategy based on the distance between the decoder output and the received input, i.e., error rate. Finally, we examine the performance of the proposed scheme over various scenarios.
AB - In this paper, we propose a game theoretical adversarial intervention detection mechanism for reliable smart road signs. A future trend in intelligent transportation systems is 'smart road signs' that incorporate smart codes (e.g., visible at infrared) on their surface to provide more detailed information to smart vehicles. Such smart codes make road sign classification problem aligned with communication settings more than conventional classification. This enables us to integrate well-established results in communication theory, e.g., error-correction methods, into road sign classification problem. Recently, vision-based road sign classification algorithms have been shown to be vulnerable against (even) small scale adversarial interventions that are imperceptible for humans. On the other hand, smart codes constructed via error-correction methods can lead to robustness against small scale intelligent or random perturbations on them. In the recognition of smart road signs, however, humans are out of the loop since they cannot see or interpret them. Therefore, there is no equivalent concept of imperceptible perturbations in order to achieve a comparable performance with humans. Robustness against small scale perturbations would not be sufficient since the attacker can attack more aggressively without such a constraint. Under a game theoretical solution concept, we seek to ensure certain measure of guarantees against even the worst case (intelligent) attackers that can perturb the signal even at large scale. We provide a randomized detection strategy based on the distance between the decoder output and the received input, i.e., error rate. Finally, we examine the performance of the proposed scheme over various scenarios.
KW - Game theory
KW - adversarial classification
KW - autonomous driving
KW - certifiable machine learning
KW - traffic sign recognition
UR - http://www.scopus.com/inward/record.url?scp=85097246383&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097246383&partnerID=8YFLogxK
U2 - 10.1109/TITS.2019.2946356
DO - 10.1109/TITS.2019.2946356
M3 - Article
AN - SCOPUS:85097246383
SN - 1524-9050
VL - 21
SP - 4995
EP - 5009
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
IS - 12
M1 - 8870234
ER -