Related papers: Assessing Reliability of Statistical Maximum Cover…
Reachability analysis evaluates system safety, by identifying the set of states a system may evolve within over a finite time horizon. In contrast to model-based reachability analysis, data-driven reachability analysis estimates reachable…
Objective: Machine learning (ML) models are increasingly used to generate electrical stimulation patterns in neuroprosthetic devices such as visual prostheses. While these models promise precise and personalized control, they also introduce…
Reliability assessment of distribution system, based on historical data and probabilistic methods, leads to an unreliable estimation of reliability indices since the data for the distribution components are usually inaccurate or…
Fuzzing is a highly effective automated testing method for uncovering software vulnerabilities. Despite advances in fuzzing techniques, such as coverage-guided greybox fuzzing, many fuzzers struggle with coverage plateaus caused by fuzz…
Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model's uncertainty is evaluated using…
Evaluating knowledge systems (LLMs, RAG, knowledge graphs, etc) faces fundamental challenges: static benchmarks are vulnerable to contamination, LLM-based judges exhibit systematic biases, and ground truth extraction requires expensive…
Fuzz testing is a crucial component of software security assessment, yet its effectiveness heavily relies on valid fuzz drivers and diverse seed inputs. Recent advancements in Large Language Models (LLMs) offer transformative potential for…
In this work, we present a novel Koopman spectrum-based reachability verification method for nonlinear systems. Contrary to conventional methods that focus on characterizing all potential states of a dynamical system over a presupposed time…
Softwarization and virtualization in 5G and beyond necessitate thorough testing to ensure the security of critical infrastructure and networks, requiring the identification of vulnerabilities and unintended emergent behaviors from protocol…
Fuzzing -- testing programs with random inputs -- has become the prime technique to detect bugs and vulnerabilities in programs. To generate inputs that cover new functionality, fuzzers require execution feedback from the program -- for…
The mushroomed Deepfake synthetic materials circulated on the internet have raised a profound social impact on politicians, celebrities, and individuals worldwide. In this survey, we provide a thorough review of the existing Deepfake…
The reliability of supervised machine learning systems depends on the accuracy and availability of ground truth labels. However, the process of human annotation, being prone to error, introduces the potential for noisy labels, which can…
Fuzzing is one of the key techniques for evaluating the robustness of programs against attacks. Fuzzing has to be effective in producing inputs that cover functionality and find vulnerabilities. But it also has to be efficient in producing…
In this paper, the output reachable estimation and safety verification problems for multi-layer perceptron neural networks are addressed. First, a conception called maximum sensitivity in introduced and, for a class of multi-layer…
Fuzzing has emerged as a powerful technique for finding security bugs in complicated real-world applications. American fuzzy lop (AFL), a leading fuzzing tool, has demonstrated its powerful bug finding ability through a vast number of…
Fuzz Testing is a well-studied area in the field of Software Maintenance and Evolution. In recent years, coverage-based Greybox fuzz testing has gained immense attention by discovering critical security level and show-stopper bugs in…
Fuzzing continues to be the most effective method for identifying security vulnerabilities in software. In the context of fuzz testing, the fuzzer supplies varied inputs to fuzz targets, which are designed to comprehensively exercise…
Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended…
The performance of a machine learning system is usually evaluated by using i.i.d.\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaining unlabeled samples may be cheaper. Stratified sampling can…
We study the robustness of conformal prediction, a powerful tool for uncertainty quantification, to label noise. Our analysis tackles both regression and classification problems, characterizing when and how it is possible to construct…