Alert button
Picture for Amir Rahmati

Amir Rahmati

Alert button

Accelerating Certified Robustness Training via Knowledge Transfer

Oct 25, 2022
Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati

Figure 1 for Accelerating Certified Robustness Training via Knowledge Transfer
Figure 2 for Accelerating Certified Robustness Training via Knowledge Transfer
Figure 3 for Accelerating Certified Robustness Training via Knowledge Transfer
Figure 4 for Accelerating Certified Robustness Training via Knowledge Transfer
Viaarxiv icon

Ares: A System-Oriented Wargame Framework for Adversarial ML

Oct 24, 2022
Farhan Ahmed, Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati

Figure 1 for Ares: A System-Oriented Wargame Framework for Adversarial ML
Figure 2 for Ares: A System-Oriented Wargame Framework for Adversarial ML
Figure 3 for Ares: A System-Oriented Wargame Framework for Adversarial ML
Figure 4 for Ares: A System-Oriented Wargame Framework for Adversarial ML
Viaarxiv icon

Transferring Adversarial Robustness Through Robust Representation Matching

Feb 21, 2022
Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati

Figure 1 for Transferring Adversarial Robustness Through Robust Representation Matching
Figure 2 for Transferring Adversarial Robustness Through Robust Representation Matching
Figure 3 for Transferring Adversarial Robustness Through Robust Representation Matching
Figure 4 for Transferring Adversarial Robustness Through Robust Representation Matching
Viaarxiv icon

Can Attention Masks Improve Adversarial Robustness?

Dec 21, 2019
Pratik Vaishnavi, Tianji Cong, Kevin Eykholt, Atul Prakash, Amir Rahmati

Figure 1 for Can Attention Masks Improve Adversarial Robustness?
Figure 2 for Can Attention Masks Improve Adversarial Robustness?
Figure 3 for Can Attention Masks Improve Adversarial Robustness?
Figure 4 for Can Attention Masks Improve Adversarial Robustness?
Viaarxiv icon

Transferable Adversarial Robustness using Adversarially Trained Autoencoders

Sep 12, 2019
Pratik Vaishnavi, Kevin Eykholt, Atul Prakash, Amir Rahmati

Figure 1 for Transferable Adversarial Robustness using Adversarially Trained Autoencoders
Figure 2 for Transferable Adversarial Robustness using Adversarially Trained Autoencoders
Figure 3 for Transferable Adversarial Robustness using Adversarially Trained Autoencoders
Figure 4 for Transferable Adversarial Robustness using Adversarially Trained Autoencoders
Viaarxiv icon

Physical Adversarial Examples for Object Detectors

Oct 05, 2018
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Florian Tramer, Atul Prakash, Tadayoshi Kohno, Dawn Song

Figure 1 for Physical Adversarial Examples for Object Detectors
Figure 2 for Physical Adversarial Examples for Object Detectors
Figure 3 for Physical Adversarial Examples for Object Detectors
Figure 4 for Physical Adversarial Examples for Object Detectors
Viaarxiv icon

Note on Attacking Object Detectors with Adversarial Stickers

Jul 23, 2018
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Dawn Song, Tadayoshi Kohno, Amir Rahmati, Atul Prakash, Florian Tramer

Figure 1 for Note on Attacking Object Detectors with Adversarial Stickers
Figure 2 for Note on Attacking Object Detectors with Adversarial Stickers
Figure 3 for Note on Attacking Object Detectors with Adversarial Stickers
Viaarxiv icon

Robust Physical-World Attacks on Deep Learning Models

Apr 10, 2018
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Amir Rahmati, Chaowei Xiao, Atul Prakash, Tadayoshi Kohno, Dawn Song

Figure 1 for Robust Physical-World Attacks on Deep Learning Models
Figure 2 for Robust Physical-World Attacks on Deep Learning Models
Figure 3 for Robust Physical-World Attacks on Deep Learning Models
Figure 4 for Robust Physical-World Attacks on Deep Learning Models
Viaarxiv icon