Related papers: SPFA: SFA on Multiple Persistent Faults

Fair Principal Component Analysis (PCA) is a problem setting where we aim to perform PCA while making the resulting representation fair in that the projected distributions, conditional on the sensitive attributes, match one another.…

Deep hashing has been extensively applied to massive image retrieval due to its efficiency and effectiveness. Recently, several adversarial attacks have been presented to reveal the vulnerability of deep hashing models against adversarial…

Implementation attacks like side-channel and fault attacks pose a considerable threat to cryptographic devices that are physically accessible by an attacker. As a consequence, devices like smart cards implement corresponding countermeasures…

We consider the use of machine learning for hypothesis testing with an emphasis on target detection. Classical model-based solutions rely on comparing likelihoods. These are sensitive to imperfect models and are often computationally…

Traditional spectrum-based fault localization (SBFL) exploits differences in a program's coverage spectrum when run on passing and failing test cases. However, such runs can provide a wealth of additional information beyond mere coverage.…

Due to the increasing complexity of Multi-Processor Systems on Chip (MPSoCs), system-level design methodologies have got a lot of attention in recent years. However, the significant gap between the system-level reliability analysis and the…

Deep neural network models are massively deployed on a wide variety of hardware platforms. This results in the appearance of new attack vectors that significantly extend the standard attack surface, extensively studied by the adversarial…

Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., black-box attacks. Existing transferable attacks tend to craft…

As Machine Learning (ML) applications rapidly grow, concerns about adversarial attacks compromising their reliability have gained significant attention. One unsupervised ML method known for its resilience to such attacks is Non-negative…

Principal component analysis (PCA) is a statistical technique commonly used in multivariate data analysis. However, PCA can be difficult to interpret and explain since the principal components (PCs) are linear combinations of the original…

Non-deterministically behaving (i.e., flaky) tests hamper regression testing as they destroy trust and waste computational and human resources. Eradicating flakiness in test suites is therefore an important goal, but automated debugging…

Neural Networks (NN) have recently emerged as backbone of several sensitive applications like automobile, medical image, security, etc. NNs inherently offer Partial Fault Tolerance (PFT) in their architecture; however, the biased PFT of NNs…

Logic locking refers to a set of techniques that can protect integrated circuits (ICs) from counterfeiting, piracy and malicious functionality changes by an untrusted foundry. It achieves these goals by introducing new inputs, called key…

We study efficient algorithms for Sparse PCA in standard statistical models (spiked covariance in its Wishart form). Our goal is to achieve optimal recovery guarantees while being resilient to small perturbations. Despite a long history of…

Motivation: Protein function prediction is a challenging task and an open problem in computational biology. The Critical Assessment of protein Function Annotation (CAFA) is a triennial, community-driven initiative that provides an…

This paper presents PSA-Eval, a failure-centered runtime evaluation framework for deployed trilingual public-space agents. The central claim is that, when the evaluation object shifts from a static input-output mapping to a runtime system,…

Side-channel analysis (SCA) poses a real-world threat by exploiting unintentional physical signals to extract secret information from secure devices. Evaluation labs also use the same techniques to certify device security. In recent years,…

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…

Third-generation artificial neural networks, Spiking Neural Networks (SNNs), can be efficiently implemented on hardware. Their implementation on neuromorphic chips opens a broad range of applications, such as machine learning-based…

Motivated by risk assessment of coastal flooding, we consider time-consuming simulators with a spatial output. The aim is to perform sensitivity analysis (SA), quantifying the influence of input parameters on the output. There are three…