Related papers: TAO: Tolerance-Aware Optimistic Verification for F…
An edge computing marketplace could enable IoT devices (Outsourcers) to outsource computation to any participating node (Contractors) in their proximity. In return, these nodes receive a reward for providing computation resources. In this…
Demographic skews in human preference data propagate systematic unfairness through reward models into aligned LLMs. We introduce Fairness Aware Reward Optimization (Faro), an in-processing framework that trains reward models under…
Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the training data. The development of tools and techniques for…
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a pivotal technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, the de facto practice of mainstream RL algorithms is to treat all…
Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…
Heterogeneous collaborative computing with NPU and CPU has received widespread attention due to its substantial performance benefits. To ensure data confidentiality and integrity during computing, Trusted Execution Environments (TEE) is…
This article proposes novel off-line test generation techniques from non-deterministic timed automata with inputs and outputs (TAIOs) in the formal framework of the tioco conformance theory. In this context, a first problem is the…
Current VLMs have demonstrated capabilities across a wide range of multimodal tasks. Typically, in a pretrained VLM, all layers are engaged by default to make predictions on downstream tasks. We find that intervening on a single layer, such…
Heterogeneous parallel error detection is an approach to achieving fault-tolerant processors, leveraging multiple power-efficient cores to re-execute software originally run on a high-performance core. Yet, its complex components, gathering…
As the Internet of Things (IoT) becomes an integral part of critical infrastructure and commercial services, runtime firmware attestation of constituent Micro-Controllers (MCUs) has become instrumental in maintaining security and trust.…
This work explores employing the concept of goal-oriented (GO) semantic communication for real-time monitoring and control. Generally, GO communication advocates for the deep integration of application targets into the network design. We…
Machine learning applications frequently come with multiple diverse objectives and constraints that can change over time. Accordingly, trained models can be tuned with sets of hyper-parameters that affect their predictive behavior (e.g.,…
The ultimate goal of verification is to guarantee the safety of deployed neural networks. Here, we claim that all the state-of-the-art verifiers we are aware of fail to reach this goal. Our key insight is that theoretical soundness…
This paper proves the threshold result, which asserts that quantum computation can be made robust against errors and inaccuracies, when the error rate, $\eta$, is smaller than a constant threshold, $\eta_c$. The result holds for a very…
The Fast Fourier Transform (FFT), as a core computation in a wide range of scientific applications, is increasingly threatened by reliability issues. In this paper, we introduce TurboFFT, a high-performance FFT implementation equipped with…
Recent work has revealed MOLE, the first practical attack to compromise GPU Trusted Execution Environments (TEEs), by injecting malicious firmware into the embedded Microcontroller Unit (MCU) of Arm Mali GPUs. By exploiting the absence of…
Discrete Event Simulation is a widely used technique that is used to model and analyze complex systems in many fields of science and engineering. The increasingly large size of simulation models poses a serious computational challenge,…
Researchers have developed neural network verification algorithms motivated by the need to characterize the robustness of deep neural networks. The verifiers aspire to answer whether a neural network guarantees certain properties with…
With the increasing complexity of computing systems, complete hardware reliability can no longer be guaranteed. We need, however, to ensure overall system reliability. One of the most important features of artificial neural networks is…
Machine learning models based on Deep Neural Networks (DNNs) are increasingly deployed in a wide range of applications ranging from self-driving cars to COVID-19 treatment discovery. To support the computational power necessary to learn a…