DeepFense: Online Accelerated Defense Against Adversarial Deep Learning

By Bita Darvish Rouhani, Mohammad Samragh, Mojan Javaheripi, Tara Javidi, Farinaz Koushanfar. 2017

50 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Hardware and Architecture

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Farinaz Koushanfar
2. Bita Darvish Rouhani
3. Hadi Esmaeilzadeh
4. Huili Chen
5. Pallabi Saikia
6. Vadlamani Ravi
7. Nam Sung Kim
8. Sanchita Basak

In Hardware and Architecture

1. Nam Sung Kim
2. Hadi Esmaeilzadeh
3. Farinaz Koushanfar
4. Cliff Young
5. Sparsh Mittal
6. Arturo Geigel

Citations in the corpus

• A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, background): “In [139] Rouhani et al., proposed an online defense framework DeepFense against adversarial deep learning.”
• Planaria: Dynamic Architecture Fission for Spatial Multi-Tenant Acceleration of Deep Neural Networks (2020, background): “There is a large body of work [1, 3, 52– 55, 71–82, 84–88, 91–93, 95, 96, 114–124] for isolated acceleration of DNNs that, although inspired our work, are not focused on multi-tenancy but rather offer various innovations to improve the speed and efficiency of DNN execution.”
• BlackMarks: Blackbox Multibit Watermarking for Deep Neural Networks (2018, background): “The rationale behind our approach is to explore the unused space within the high dimensional DNN [17] for WM embedding.”