Abstract | ||
---|---|---|
Autonomous driving and other applications depend critically on sensor data to function correctly. The most common sensor data is visual data, processed with computer vision algorithms. The effectiveness of these algorithms has markedly improved with the advent of deep learning. Yet, at the same time, research has shown these algorithms bring serious security concerns. Small, even invisible perturbations can completely change the algorithm's interpretation of the data. Basically, we cannot at present trust a car to read a road sign. In this position paper we present the difficulties with reliance on current deep learning algorithms and outline paths forward. In particular, we analyze the security tradeoffs of an alternative approach for visual communication based on visible light communications (VLC). |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/CISS.2018.8362320 | 2018 52nd Annual Conference on Information Sciences and Systems (CISS) |
Keywords | Field | DocType |
visual channel,car,autonomous driving,common sensor data,visual data,computer vision algorithms,serious security concerns,invisible perturbations,road sign,security tradeoffs,visual communication,visible light communications,deep learning algorithms | Computer science,Visualization,Position paper,Computer network,Communication channel,Visible light communication,Robustness (computer science),Human–computer interaction,Computer vision algorithms,Artificial intelligence,Visual communication,Deep learning | Conference |
ISBN | Citations | PageRank |
978-1-5386-0580-6 | 0 | 0.34 |
References | Authors | |
12 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Richard Chow | 1 | 19 | 4.07 |
Hsin-Mu Tsai | 2 | 305 | 29.74 |