Protecting adaptive sampling from information leakage on low-power sensors

Kannan, Tejas; Hoffmann, Henry

doi:10.1145/3503222.3507775

Cited by 4 publications

(3 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering more metrics, such as ROM, RAM, latency, energy, and throughput, the best algorithms for 16-bit are Fantomas-128, Robin-128, SPECH-96, AES-128, PRINCE-128, DESXL-184, SEA-96, and PRESENT-80. The authors [74] tested the information leaking in low-power sensors and proposed a new approach using adaptive group encoding (AGE) to protect communication between the devices. The new method was tested in the TI MSP430 MCU, consuming 0.154 mJ for encoding a message.…”

Section: Discussionmentioning

confidence: 99%

Discussion on Secure Standard Network of Sensors Powered by Microbial Fuel Cells

da Rocha,

Caruso,

Pereira

et al. 2023

Sensors

View full text Add to dashboard Cite

Everyday tasks use sensors to monitor and provide information about processes in different scenarios, such as monitoring devices in manufacturing or homes. Sensors need to communicate, with or without wires, while providing secure information. Power can be derived from various energy sources, such as batteries, electrical power grids, and energy harvesting. Energy harvesting is a promising way to provide a sustainable and renewable source to power sensors by scavenging and converting energy from ambient energy sources. However, low energy is harvested through these methods. Therefore, it is becoming a challenge to design and deploy wireless sensor networks while ensuring the sensors have enough power to perform their tasks and communicate with each other through careful management and optimization, matching energy supply with demand. For this reason, data cryptography and authentication are needed to protect sensor communication. This paper studies how energy harvested with microbial fuel cells can be employed in algorithms used in data protection during sensor communication.

show abstract

Section: Discussionmentioning

confidence: 99%

Discussion on Secure Standard Network of Sensors Powered by Microbial Fuel Cells

da Rocha,

Caruso,

Pereira

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…63 Of these frameworks, the most pertinent is AGE. 64 AGE prevents information leakage from message sizes induced by adaptive sampling. Similar to DRSC, AGE closes this side-channel by creating fixed-length messages.…”

Section: Side-channels Via Communication Patternsmentioning

confidence: 99%

A security analysis of compressed communication in distributed deep neural networks

Kannan,

Dimassimo,

Haga

2024

Assurance and Security for AI-enabled Systems

View full text Add to dashboard Cite

Deep distributed neural networks (DDNNs) use partitioning and data compression to perform neural network inference under the tight resource constraints of edge computing systems. Existing DDNN applications focus on efficient execution without accounting for how these features impact data privacy. In this work, we develop a side-channel attack that exploits the use of compressed communication in DDNN systems. We demonstrate how the size of compressed messages provides information about the DDNN's results, even when the system uses data encryption. We demonstrate this side-channel by developing a probabilistic attack that uses message sizes to infer the DDNN's results with over 2.3× the accuracy of random guessing. In the worst case, our attack discovers over 90% of the DDNN's outputs.We mitigate this side-channel through a novel defense called dropout stable compression (DRSC), which guarantees fixed-length messages for DDNNs. DRSC acts as a wrapper around lossless compression and delivers an overall compression ratio equal to that of the underlying lossless method. To achieve this behavior, DRSC controls the compressed size through Dropout. 1 DRSC limits the impact of Dropout on the DDNN's accuracy by dropping values with the smallest magnitude. This design allows DRSC to eliminate the discovered side-channel while displaying negligible overhead and an inference accuracy within 0.3 percentage points (i.e., 0.3%) of existing systems. With this behavior, DRSC enables resource constrained systems to gain the benefits of DDNNs without suffering from the privacy issues stemming from data compression.

show abstract

“…In wireless sensor nodes, each sampling task includes sensor reading, data processing, and wireless communication. Too frequent sensor sampling may drain the battery very quickly, especially in the presence of power-hungry sensors [6], [11]. Therefore, energy-aware adaptive sampling can help increase the lifetime of wireless sensor nodes by reducing the sampling rate when the energy availability is low [12].…”

Section: Introductionmentioning

confidence: 99%

Predictive Energy-Aware Adaptive Sampling with Deep Reinforcement Learning

Heo

Mayer

Magno

2022

2022 29th IEEE International Conference on Electronics, Circuits and Systems (ICECS)

View full text Add to dashboard Cite

Energy harvesting can enable wireless smart sensors to be self-sustainable by allowing them to gather energy from the environment. However, since the energy availability changes dynamically depending on the environment, it is difficult to find an optimal energy management strategy at design time. One existing approach to reflecting dynamic energy availability is energy-aware adaptive sampling, which changes the sampling rate of a sensor according to the energy state. This work proposes deep reinforcement learning-based predictive adaptive sampling for a wireless sensor node. The proposed approach applies deep reinforcement learning to find an effective adaptive sampling strategy based on the harvesting power and energy level. In addition, the proposed approach enables predictive adaptive sampling by designing adaptive sampling models that consider the trend of energy state. The evaluation results show that the predictive models can successfully manage the energy budget reflecting dynamic energy availability, maintaining a stable energy state for a up to 11.5% longer time.

show abstract

Protecting adaptive sampling from information leakage on low-power sensors

Cited by 4 publications

References 100 publications

Discussion on Secure Standard Network of Sensors Powered by Microbial Fuel Cells

Discussion on Secure Standard Network of Sensors Powered by Microbial Fuel Cells

A security analysis of compressed communication in distributed deep neural networks

Predictive Energy-Aware Adaptive Sampling with Deep Reinforcement Learning

Contact Info

Product

Resources

About