Difference between revisions of "Rouhani2018deepfense"
From ACES
(Import from BibTeX) |
m (Default pdf) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
|url=https://arxiv.org/abs/1709.02538 | |url=https://arxiv.org/abs/1709.02538 | ||
|abstract=<p><span style="font-family: \"Lucida Grande\", helvetica, arial, verdana, sans-serif; font-size: 14.4px;">Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, online detection of malicious inputs is of utmost importance. We propose DeepFense, the first end-to-end automated framework that simultaneously enables efficient and safe execution of DL models. DeepFense formalizes the goal of thwarting adversarial attacks as an optimization problem that minimizes the rarely observed regions in the latent feature space spanned by a DL network. To solve the aforementioned minimization problem, a set of complementary but disjoint modular redundancies are trained to validate the legitimacy of the input samples in parallel with the victim DL model. DeepFense leverages hardware/software/algorithm co-design and customized acceleration to achieve just-in-time performance in resource-constrained settings. The proposed countermeasure is unsupervised, meaning that no adversarial sample is leveraged to train modular redundancies. We further provide an accompanying API to reduce the non-recurring engineering cost and ensure automated adaptation to various platforms. Extensive evaluations on FPGAs and GPUs demonstrate up to two orders of magnitude performance improvement while enabling online adversarial sample detection.</span></p> | |abstract=<p><span style="font-family: \"Lucida Grande\", helvetica, arial, verdana, sans-serif; font-size: 14.4px;">Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, online detection of malicious inputs is of utmost importance. We propose DeepFense, the first end-to-end automated framework that simultaneously enables efficient and safe execution of DL models. DeepFense formalizes the goal of thwarting adversarial attacks as an optimization problem that minimizes the rarely observed regions in the latent feature space spanned by a DL network. To solve the aforementioned minimization problem, a set of complementary but disjoint modular redundancies are trained to validate the legitimacy of the input samples in parallel with the victim DL model. DeepFense leverages hardware/software/algorithm co-design and customized acceleration to achieve just-in-time performance in resource-constrained settings. The proposed countermeasure is unsupervised, meaning that no adversarial sample is leveraged to train modular redundancies. We further provide an accompanying API to reduce the non-recurring engineering cost and ensure automated adaptation to various platforms. Extensive evaluations on FPGAs and GPUs demonstrate up to two orders of magnitude performance improvement while enabling online adversarial sample detection.</span></p> | ||
|year=2018 | |||
|booktitle=ICCAD | |booktitle=ICCAD | ||
|title=DeepFense: Online Accelerated Defense Against Adversarial Deep Learning | |title=DeepFense: Online Accelerated Defense Against Adversarial Deep Learning | ||
|entry=inproceedings | |entry=inproceedings | ||
| | |pdf=Rouhani2018deepfense.pdf | ||
}} | }} | ||
Latest revision as of 17:39, 9 November 2021
| Rouhani2018deepfense | |
|---|---|
| entry | inproceedings |
| address | |
| annote | |
| author | Bita Rouhani and Mohammad Samragh and Mojan Javaheripi and Farinaz Koushanfar and Javidi, Tara |
| booktitle | ICCAD |
| chapter | |
| edition | |
| editor | |
| howpublished | |
| institution | |
| journal | |
| month | |
| note | |
| number | |
| organization | |
| pages | |
| publisher | |
| school | |
| series | |
| title | DeepFense: Online Accelerated Defense Against Adversarial Deep Learning |
| type | |
| volume | |
| year | 2018 |
| doi | |
| issn | |
| isbn | |
| url | https://arxiv.org/abs/1709.02538 |
| Rouhani2018deepfense.pdf | |
Email:
farinaz@ucsd.edu
farinaz@ucsd.edu
Address:
Electrical & Computer Engineering
University of California, San Diego
9500 Gilman Drive, MC 0407
Jacobs Hall, Room 6401
La Jolla, CA 92093-0407
Electrical & Computer Engineering
University of California, San Diego
9500 Gilman Drive, MC 0407
Jacobs Hall, Room 6401
La Jolla, CA 92093-0407
Lab Location: EBU1-2514
University of California San Diego
9500 Gilman Dr, La Jolla, CA 92093
University of California San Diego
9500 Gilman Dr, La Jolla, CA 92093