SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their issues with robustness, which is essential for safety critical applications such as autonomous driving. This has motivated much recent work on adversarial attacks for DNNs, which mostly focus on pixel-level perturbations void of semantic meaning. In contrast, we present a general framework for adversarial black box attacks on agents, which are intimately related to the semantics of the task being performed by the agent. To do this, our proposed adversary (denoted as BBGAN) is trained to appropriately parametrize the environment (black box) with which the agent interacts, such that this agent performs poorly on its dedicated task. We illustrate the application of our BBGAN framework on three different tasks (primarily targeting aspects of autonomous navigation): object detection, self-driving, and autonomous UAV racing. On these tasks, our approach can be used to generate failure cases that fool an agent consistently.
Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Abdullah Hamdi (edit)
Matthias Müller (add twitter)
Bernard Ghanem (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
12/05/18 06:01PM
11,240
3,022
Tweets
desantis: RT @Memoirs: SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications. https://t.co/UlKUtKdv9I
desantis: RT @Memoirs: SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications. https://t.co/UlKUtKdv9I
Memoirs: SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications. https://t.co/UlKUtKdv9I
arxivml: "SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications", Abdullah Hamdi, Matthias Müller, Berna… https://t.co/HKzWbSgGTk
BrundageBot: SADA: Semantic Adversarial Diagnostic Attacks for Autonomous Applications. Abdullah Hamdi, Matthias Müller, and Bernard Ghanem https://t.co/cTty7aHltu
Images
Related