相关论文: Verification of Bit-Flip Attacks against Quantized…

Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and…

Recently proposed methods for 1-bit and 1.58-bit quantization aware training investigate the performance and behavior of these methods in the context of large language models, finding state-of-the-art performance for models with more than…

In this paper, we present Zero-data Based Repeated bit flip Attack (ZeBRA) that precisely destroys deep neural networks (DNNs) by synthesizing its own attack datasets. Many prior works on adversarial weight attack require not only the…

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…

Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit. However, there is still a huge performance gap between Binary Neural Networks (BNNs) and their full-precision (FP) counterparts. As…

As the demand for highly secure and dependable lightweight systems increases in the modern world, Physically Unclonable Functions (PUFs) continue to promise a lightweight alternative to high-cost encryption techniques and secure key…

Quantized Neural Networks (QNNs) are increasingly deployed in edge and resource-constrained environments due to their efficiency in computation and memory usage. While shown to distort the gradient landscape and weaken conventional…

The widely held belief that BQP strictly contains BPP raises fundamental questions: if we cannot efficiently compute predictions for the behavior of quantum systems, how can we test their behavior? In other words, is quantum mechanics…

Despite the functional success of deep neural networks (DNNs), their trustworthiness remains a crucial open challenge. To address this challenge, both testing and verification techniques have been proposed. But these existing techniques…

Validating wireless protocol implementations is challenging. Today's approaches require labor-intensive experimental setup and manual trace investigation, but produce poor coverage and inaccurate and irreproducible results. We present…

Implementations of artificial neural networks (ANNs) might lead to failures, which are hardly predicted in the design phase since ANNs are highly parallel and their parameters are barely interpretable. Here, we develop and evaluate a novel…

We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural Networks (FNNs): rational FNNs with exact rational weights, quantised FNNs whose weights…

Deep Neural Networks (DNNs) can be catastrophically disrupted by flipping only a handful of parameter bits. We introduce Deep Neural Lesion (DNL), a data-free and optimizationfree method that locates critical parameters, and an enhanced…

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications.…

Quantization can preserve predictive accuracy under low-bit deployment while silently breaking algorithmic recourse: an actionable change that flips a decision before quantization may fail after quantization, or become substantially more…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks. To this end, many defense approaches that attempt to improve the robustness of DNNs have been proposed. In a separate and yet related area,…

Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce unintuitive outputs. One key approach to verify and mitigate such robustness issues is to falsify…

Quantum reinforcement learning (QRL) aims to use quantum effects to create sequential decision-making policies that achieve tasks more effectively than their classical counterparts. However, QRL policies face uncertainty from quantum…

Certifying the safety or robustness of neural networks against input uncertainties and adversarial attacks is an emerging challenge in the area of safe machine learning and control. To provide such a guarantee, one must be able to bound the…

We present and experimentally demonstrate a novel approach to verification and benchmarking of quantum computing, implementing it on an ion-trap quantum computer. Unlike previous information-theoretically secure verification protocols,…