activity
20122021
most citedSESAME: Software defined Enclaves to Secure Inference Accelerators with Multi-tenant Execution

6 citations · 10 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CR20212 cited

Bandwidth Utilization Side-Channel on ML Inference Accelerators

Sarbartha Banerjee, Shijia Wei, Prakash Ramrakhyani +1

Accelerators used for machine learning (ML) inference provide great performance benefits over CPUs. Securing confidential model in inference against off-chip side-channel attacks i…

cs.CR2021

Power-Based Attacks on Spatial DNN Accelerators

Ge Li, Mohit Tiwari, Michael Orshansky

With proliferation of DNN-based applications, the confidentiality of DNN model is an important commercial goal. Spatial accelerators, that parallelize matrix/vector operations, are…

cs.CY2021

Challenges in cybersecurity: Lessons from biological defense systems

Edward Schrom, Ann Kinzig, Stephanie Forrest +18

We explore the commonalities between methods for assuring the security of computer systems (cybersecurity) and the mechanisms that have evolved through natural selection to protect…

cs.CR20206 cited

SESAME: Software defined Enclaves to Secure Inference Accelerators with Multi-tenant Execution

Sarbartha Banerjee, Prakash Ramrakhyani, Shijia Wei +1

Hardware-enclaves that target complex CPU designs compromise both security and performance. Programs have little control over micro-architecture, which leads to side-channel leaks,…

cs.CR2018

The Shape of Alerts: Detecting Malware Using Distributed Detectors by Robustly Amplifying Transient Correlations

Mikhail Kazdagli, Constantine Caramanis, Sanjay Shakkottai +1

We introduce a new malware detector - Shape-GD - that aggregates per-machine detectors into a robust global detector. Shape-GD is based on two insights: 1. Structural: actions such…

cs.CR2017

Exploiting Latent Attack Semantics for Intelligent Malware Detection

Mkhail Kazdagli, Constantine Caramanis, Sanjay Shakkottai +1

Behavioral malware detectors promise to expose previously unknown malware and are an important security primitive. However, even the best behavioral detectors suffer from high fals…