We present BISen, a framework for efficient and reliable convolutional neural network (CNN) inference on battery-free, energy-harvesting IoT sensor nodes. Battery-powered deployments suffer from limited lifetimes, high replacement costs, and environmental impacts, problems that will intensify as IoT scales to billions of devices. Energy-harvesting nodes remove batteries but face intermittent power, resulting in frequent failures that corrupt the intermediate CNN state, require costly checkpointing and rollback, and amplify non-volatile memory (NVM) traffic under tight on-chip memory constraints, leaving little harvested energy for useful sensing and inference. BISen introduces a reactive intermittent execution model for CNN workloads on off-the-shelf ultra-low-power microcontrollers. An energy-aware state machine with a safe-stop mechanism halts execution before brownout, while selective checkpointing preserves only the minimal CNN state needed for forward progress. This enables seamless resumption across power cycles while sharply reducing NVM reads/writes and memory-access overheads. Across two commercial MCU+radio platforms, three real harvested power traces, and nine CNNs, BISen cuts NVM operations by up to 86.4%, reduces standby/load/store operations by up to 94.1%, 94.5%, and 90.7%, and improves sensing throughput by about 1.3−1.4× compared to a state-of-the-art reactive baseline under the same energy budget, enabling long-lived, battery-free, carbon-aware IoT deployments.

State re-sharding can reduce cross-shard transaction ratios, which improves the scalability of blockchain systems. However, unavoidable cross-shard transactions and account-locking mechanisms can lead to security risks (read-write conflicts) and performance bottlenecks (low synchronization efficiency). Therefore, this paper proposes a secure and efficient read-write synchronization model for cross-shard transactions in blockchain state re-sharding via a lightweight Global State Tree (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{GT}$</tex-math></inline-formula>). The model consists of intra-shard and inter-shard state consistency modules. The intra-shard module includes two methods: account state read-write and account record update. The former allows local shard committees to track account state changes and prevent the use of expired account states, while the latter incorporates account records within maximum latency into an account state data structure, thereby enhancing the traceability and verification efficiency of update history. In the inter-shard module, a transaction processing method with a global takeover mechanism is proposed during the re-sharding window. By using validated data in the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{GT}$</tex-math></inline-formula>, the method achieves non-blocking global coordination and account reallocation. Experimental results demonstrate that the proposed model increases transaction throughput and reduces transaction latency compared to bases under Byzantine conditions.

Federated learning (FL) enables privacy-preserving distributed machine learning by training models on edge client devices using their local data without revealing their raw data. In edge environments, various applications require different neural network models, making it crucial to perform joint training of multiple models on edge devices, known as multi-task FL. While existing multi-task FL approaches enhance resource utilization on edge devices through adaptive resource configuration or client selection, optimizing either of these aspects alone may lead to suboptimality. Therefore, in this paper, we explore a joint client selection and resource configuration method called JCSRC for multi-task FL, aiming to maximize energy efficiency in environments with limited computation and communication resources and heterogeneous client devices. Firstly, we formalize this problem as a mixed-integer nonlinear programming problem considering all these characteristics and prove its NP-hardness. To address this problem, we first design a multi-agent reinforcement learning (MARL)-based client selection method that selects appropriate clients for each task to train their models. The MARL method makes client selection decisions based on the clients’ data quality, energy efficiency, communication, and computation capacity to ensure fast convergence and energy efficiency. Then, we design a particle swarm optimization (PSO)-based resource configuration scheme that configures appropriate computation and bandwidth resources for each task on each client. The PSO scheme makes resource configuration decisions based on theoretically derived optimal CPU frequency and bandwidth to achieve high energy efficiency. Finally, we carry out extensive simulations and testbed-based experiments to validate our proposed JCSRC. The results demonstrate that, in comparison to state-of-the-art solutions, JCSRC can save energy consumption by up to 59% to achieve the target accuracy.

QARMAv2, a family of lightweight block ciphers introduced in ToSC 2023, is an evolution of the original QARMA design, specifically constructed to accommodate more extended tweak values while simultaneously enhancing security measures. In this paper, for the first time, we present differential fault analysis (DFA) of all the QARMAv2 variants by introducing an approach to utilize the fault propagation patterns at the nibble level, with the goal of identifying relevant faulty ciphertexts and vulnerable fault positions. Introducing six random nibble faults strategically into the (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r</i> – 1)-th and (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r</i> – 2)-th backward rounds of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r</i>-round QARMAv2-64 significantly reduces the secret key space from 2<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">128</sup> to 2<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">32</sup>. Additionally, when targeting QARMAv2-128-128, it demands the introduction of six random nibble faults to effectively reduce the secret key space from 2<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">128</sup> to a remarkably reduced 2<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">24</sup>. To conclude, we also explore the potential extension of our methods to conduct DFA on other versions of QARMAv2. To the best of our knowledge, this marks the first instance of a differential fault attack targeting the QARMAv2 tweakable block cipher family, signifying an important direction in cryptographic analysis.

Sharding is a promising solution to enhance blockchain scalability. While deploying more shards of smaller sizes for a given network scale can significantly boost performance, it also heightens the risk of shard failures. In many existing sharding systems, the failure of a single shard can compromise the entire system. Therefore, to ensure safety, current systems often require each shard to contain hundreds of consensus nodes to prevent crashes, adversely affecting scalability. In this paper, we propose Levee, a blockchain sharding system capable of tolerating shard failures. When a shard malfunctions, Levee can swiftly detect, isolate, and autonomously recover the faulty shard, allowing other shards to operate without interruption. This fault-tolerance feature enables Levee to reduce shard sizes by 73.7% and increase the number of shards by 3.25 times, all without sacrificing security. When tested in a scenario with 7000 nodes, Levee demonstrated a 14.34 times increase in throughput and a 65% decrease in transaction latency compared to traditional non-fault-tolerant sharding systems.

The impressive performance of transformer models has sparked the deployment of intelligent applications on resource-constrained edge devices. However, ensuring high-quality service for real-time edge systems is a significant challenge due to the considerable computational demands and resource requirements of these models. Existing strategies typically either offload transformer computations to other devices or directly deploy compressed models on individual edge devices. These strategies, however, result in either considerable communication overhead or suboptimal trade-offs between accuracy and efficiency. To tackle these challenges, we propose a collaborative inference system for general transformer models, termed CoFormer. The central idea behind CoFormer is to exploit the divisibility and integrability of transformer. An off-the-shelf large transformer can be decomposed into multiple smaller models for distributed inference, and their intermediate results are aggregated to generate the final output. We formulate an optimization problem to minimize both inference latency and accuracy degradation under heterogeneous hardware constraints. DeBo algorithm is proposed to first solve the optimization problem to derive the decomposition policy, and then progressively calibrate decomposed models to restore performance. We demonstrate the capability to support a wide range of transformer models on heterogeneous edge devices, achieving up to 3.1× inference speedup with large transformer models. Notably, CoFormer enables the efficient inference of GPT2-XL with 1.6 billion parameters on edge devices, reducing memory requirements by 76.3%. CoFormer can also reduce energy consumption by approximately 40% while maintaining satisfactory inference performance.

The robustness of subnetworks for the interconnection network of a computer system is an important consideration for the system performance. It can be measured by the extent to which subnetworks can stay fault-free when faults are present in the system. In this paper, we evaluate the subnetwork robustness for the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i>-dimensional split-star network <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{n}^{2}$</tex-math></inline-formula>. Let <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{n-m}^{2}, 1 \leq m \leq n-3$</tex-math></inline-formula> , be a subnetwork of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{n}^{2}$</tex-math></inline-formula>, and let <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> be the node reliability, the probability that a single node remains fault-free. We determine two values that reflect how robust <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{n-m}^{2}$</tex-math></inline-formula> subnetworks are, from two perspectives. We first establish the upper/lower bounds for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{F}_{m} (S_{n}^{2})$</tex-math></inline-formula>, the minimum number of faulty nodes to make all <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{n-m}^{2}$</tex-math></inline-formula> subnetworks faulty. Then, we determine the subnetwork reliability, denoted by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}_{m} (S_{n}^{2}, p)$</tex-math></inline-formula>, which is the probability that at least one fault-free <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{n-m}^{2}$</tex-math></inline-formula> subnetwork exists in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$S_{n}^{2}$</tex-math></inline-formula>, given the node reliability <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i>. The upper/lower bounds and an approximation expression for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}_{m} (S_{n}^{2}, p)$</tex-math></inline-formula> are obtained. We also propose a simulation method to estimate <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}_{m} (S_{n}^{2}, p)$</tex-math></inline-formula>. The experimental results show that a) when <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> is relatively low, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}_{m} (S_{n}^{2}, p)$</tex-math></inline-formula> can be approximated by the mean value of its upper and lower bounds, or the estimation value by the approximation expression; b) when <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> is high, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}_{m} (S_{n}^{2}, p)$</tex-math></inline-formula> can be more accurately estimated by our simulation method.

State access is a critical part of smart contract execution which seriously affects the efficiency of smart contract execution in the mainstream Ethereum blockchain. To reduce state access latency, existing studies typically require manual source code modifications, which in practice may deliver limited performance gains and shift the burden to developers. In this paper, we propose CROSC to reduce state access latency and improve smart contract execution efficiency by a compilation-runtime joint optimization approach. CROSC consists of three key parts: 1) a runtime memory management mechanism named Fast State Memory (FastSM) to fully utilize the working memory and provide the context for the contract compiler; 2) a State Variable Address Relocation (SVAR) strategy to minimize costly persistent storage operations by precisely redirecting state variable access targets during compilation; 3) a one-shot unpacking design that eliminates frequent decoding overhead for low-bitwidth state variables. Preliminary experimental results highlight that, compared with the baseline compilation and runtime system of Ethereum, CROSC can achieve 2.5× and 7.5× speedups for single state load and store operations, respectively. CROSC reduces state access latency by up to 81.3%, and overall contract execution latency by 32.9% on average across 14 typical types of smart contracts. Extended evaluations on ERC20 and ERC721 token standard contracts show that CROSC delivers significant benefits in critical areas while remaining unobtrusive for less intensive state operations.

Traditional structural tests are powerful automatic approaches for capturing faulty behavior in integrated circuits. Besides the ease of generating test patterns, structural methods are known to be able to cover a vast but incomplete spectrum of all possible faults in a System-on-Chip (SoC). A new step in the manufacturing test flow has been added to fill the leftover gaps of structural tests, called the System-Level Test (SLT), which resembles the final workload, and environment. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">This work illustrates how to build up an automated generation engine to synthesize SLT programs that effectively attack structural test weaknesses from both a holistic and an analytical perspective. The methodology targets the crossbar module, as one of the most critical areas in the SoC, and it simultaneously creates a ripple effect across the un-core logic. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Experimental results are conducted on an automotive SoC manufactured by STMicroelectronics.