Energy-Latency Attacks: A New Adversarial Threat to Deep Learning
This work highlights a new adversarial threat for AI practitioners and researchers, focusing on vulnerabilities in energy-efficient hardware and adaptable DNNs, but it is incremental as it surveys existing research rather than introducing novel methods.
This paper addresses the vulnerability of deep neural networks to energy-latency attacks, which exploit efficiency-focused designs to increase latency and energy usage, potentially causing denial-of-service attacks, and provides a comprehensive survey categorizing, analyzing, and comparing existing attack strategies and defenses.
The growing computational demand for deep neural networks ( DNNs) has raised concerns about their energy consumption and carbon footprint, particularly as the size and complexity of the models continue to increase. To address these challenges, energy-efficient hardware and custom accelerators have become essential. Additionally, adaptable DNN s are being developed to dynamically balance performance and efficiency. The use of these strategies became more common to enable sustainable AI deployment. However, these efficiency-focused designs may also introduce vulnerabilities, as attackers can potentially exploit them to increase latency and energy usage by triggering their worst-case-performance scenarios. This new type of attack, called energy-latency attacks, has recently gained significant research attention, focusing on the vulnerability of DNN s to this emerging attack paradigm, which can trigger denial-of-service ( DoS) attacks. This paper provides a comprehensive overview of current research on energy-latency attacks, categorizing them using the established taxonomy for traditional adversarial attacks. We explore different metrics used to measure the success of these attacks and provide an analysis and comparison of existing attack strategies. We also analyze existing defense mechanisms and highlight current challenges and potential areas for future research in this developing field. The GitHub page for this work can be accessed at https://github.com/hbrachemi/Survey_energy_attacks/