Sorry, you need to enable JavaScript to visit this website.

ICASSP 2020

ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The ICASSP 2020 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world. Visit website.

Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems


Resistive switching memory technologies (RRAM) are seen by most of the scientific community as an enabler for Edge-level applications such as embedded deep Learning, AI or signal processing of audio and video signals. However, going beyond a ``simple'' replacement of eFlash in micro-controller and introducing RRAM inside the memory hierarchy is not a straightforward move. Indeed, integrating a RRAM technology inside the cache hierarchy requires higher endurance requirement than for eFlash replacement, and thus necessitates relaxed programming conditions.

Paper Details

Authors:
Alexandre Levisse, Marco Rios, Miguel Peon, David Atienza
Submitted On:
4 February 2020 - 8:19am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_VF.pdf

(105)

Subscribe

[1] Alexandre Levisse, Marco Rios, Miguel Peon, David Atienza, "Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4971. Accessed: Sep. 26, 2020.
@article{4971-20,
url = {http://sigport.org/4971},
author = {Alexandre Levisse; Marco Rios; Miguel Peon; David Atienza },
publisher = {IEEE SigPort},
title = {Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems},
year = {2020} }
TY - EJOUR
T1 - Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems
AU - Alexandre Levisse; Marco Rios; Miguel Peon; David Atienza
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4971
ER -
Alexandre Levisse, Marco Rios, Miguel Peon, David Atienza. (2020). Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems. IEEE SigPort. http://sigport.org/4971
Alexandre Levisse, Marco Rios, Miguel Peon, David Atienza, 2020. Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems. Available at: http://sigport.org/4971.
Alexandre Levisse, Marco Rios, Miguel Peon, David Atienza. (2020). "Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems." Web.
1. Alexandre Levisse, Marco Rios, Miguel Peon, David Atienza. Exploration Methodology for BTI-Induced Failures on RRAM-Based Edge AI Systems [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4971

Performance Bounds for Displaced Sensor Automotive Radar Imaging


In automotive radar imaging, displaced sensors offer improvement in localization accuracy by jointly processing the data acquired from multiple radar units, each of which may have limited individual resources. In this paper, we derive performance bounds on the estimation error of target parameters processed by displaced sensors that correspond to several independent radars mounted at different locations on the same vehicle. Unlike previous studies, we do not assume a very accurate time synchronization among the sensors.

Paper Details

Authors:
Submitted On:
17 February 2020 - 8:37pm
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2020_displacedSensors (10).pdf

(69)

Subscribe

[1] , "Performance Bounds for Displaced Sensor Automotive Radar Imaging", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4970. Accessed: Sep. 26, 2020.
@article{4970-20,
url = {http://sigport.org/4970},
author = { },
publisher = {IEEE SigPort},
title = {Performance Bounds for Displaced Sensor Automotive Radar Imaging},
year = {2020} }
TY - EJOUR
T1 - Performance Bounds for Displaced Sensor Automotive Radar Imaging
AU -
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4970
ER -
. (2020). Performance Bounds for Displaced Sensor Automotive Radar Imaging. IEEE SigPort. http://sigport.org/4970
, 2020. Performance Bounds for Displaced Sensor Automotive Radar Imaging. Available at: http://sigport.org/4970.
. (2020). "Performance Bounds for Displaced Sensor Automotive Radar Imaging." Web.
1. . Performance Bounds for Displaced Sensor Automotive Radar Imaging [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4970

Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples


We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN image manipulation detector to other detectors (a fully connected neural network and a linear SVM) that rely on a random subset of the features extracted from the flatten layer of the original network.

Paper Details

Authors:
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang
Submitted On:
30 January 2020 - 12:06pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP20-final..pdf

(81)

Subscribe

[1] Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, "Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4968. Accessed: Sep. 26, 2020.
@article{4968-20,
url = {http://sigport.org/4968},
author = {Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang },
publisher = {IEEE SigPort},
title = {Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples},
year = {2020} }
TY - EJOUR
T1 - Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples
AU - Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4968
ER -
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples. IEEE SigPort. http://sigport.org/4968
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, 2020. Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples. Available at: http://sigport.org/4968.
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). "Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples." Web.
1. Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4968

Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples


We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN image manipulation detector to other detectors (a fully connected neural network and a linear SVM) that rely on a random subset of the features extracted from the flatten layer of the original network.

Paper Details

Authors:
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang
Submitted On:
30 January 2020 - 12:03pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP20-final..pdf

(57)

Subscribe

[1] Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, "Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/4967. Accessed: Sep. 26, 2020.
@article{4967-20,
url = {http://sigport.org/4967},
author = {Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang },
publisher = {IEEE SigPort},
title = {Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples},
year = {2020} }
TY - EJOUR
T1 - Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples
AU - Mauro Barni; Ehsan Nowroozi; Benedetta Tondi; Bowen Zhang
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/4967
ER -
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples. IEEE SigPort. http://sigport.org/4967
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang, 2020. Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples. Available at: http://sigport.org/4967.
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. (2020). "Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples." Web.
1. Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang. Effectiveness of Random Deep Feature Selection for securing image manipulation detectors against adversarial examples [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/4967

Pages