6 papers
Deep Learning Latency Attacks and Defenses: A Cross-Domain Survey of Availability Threats
Zonghua Gu, Zeyu Gao, Amin Saremi +1
Adversarial machine learning has focused mainly on integrity, but availability is an increasingly consequential complement. Latency attacks (also energy-latency attacks) increase i…
Autonomous Systems Dependability in the era of AI: Design Challenges in Safety, Security, Reliability and Certification
Behnaz Ranjbar, Kirankumar Raveendiran, Sudeep Pasricha +3
The design of embedded safety-critical systems such as those used in next-generation automotive and autonomous platforms, is increasingly challenged by escalating system complexity…
A shallow dive into the depths of non-termination checking for C programs
Ravindra Metta, Hrishikesh Karmarkar, Kumar Madhukar +3
Checking for Non-Termination (NT) of a given program P, i.e., determining if P has at least one non-terminating run, is an undecidable problem that continues to garner significant…
Enhancing Split Computing and Early Exit Applications through Predefined Sparsity
Luigi Capogrosso, Enrico Fraccaroli, Giulio Petrozziello +4
In the past decade, Deep Neural Networks (DNNs) achieved state-of-the-art performance in a broad range of problems, spanning from object classification and action recognition to sm…
MTL-Split: Multi-Task Learning for Edge Devices using Split Computing
Luigi Capogrosso, Enrico Fraccaroli, Samarjit Chakraborty +2
Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promisi…
To Balance or to Not? Battery Aging-Aware Active Cell Balancing for Electric Vehicles
Enrico Fraccaroli, Seongik Jang, Logan Stach +3
Due to manufacturing variabilities and temperature gradients within an electric vehicle's battery pack, the capacities of cells in it decrease differently over time. This reduces t…