English
Related papers

Related papers: PVF (Parameter Vulnerability Factor): A Scalable M…

200 papers

The quality assessment of Artificial Intelligence (AI) systems is a fundamental challenge due to their inherently probabilistic nature. Standards such as ISO/IEC 25059 provide a quality model, but they lack practical and statistically…

The AI trustworthiness crisis threatens to derail the artificial intelligence revolution, with regulatory barriers, security vulnerabilities, and accountability gaps preventing deployment in critical domains. Current AI systems operate on…

Cryptography and Security · Computer Science 2025-11-26 Vineeth Sai Narajala , Manish Bhatt , Idan Habler , Ronald F. Del Rosario , Ads Dawson

Object detection neural network models need to perform reliably in highly dynamic and safety-critical environments like automated driving or robotics. Therefore, it is paramount to verify the robustness of the detection under unexpected…

Computer Vision and Pattern Recognition · Computer Science 2022-09-08 Syed Qutub , Florian Geissler , Yang Peng , Ralf Grafe , Michael Paulitsch , Gereon Hinz , Alois Knoll

Recent advances in automated vulnerability detection have achieved potential results in helping developers determine vulnerable components. However, after detecting vulnerabilities, investigating to fix vulnerable code is a non-trivial…

Software Engineering · Computer Science 2023-06-27 Hieu Dinh Vo , Son Nguyen

Mainstream software applications and tools are the configurable platforms with an enormous number of parameters along with their values. Certain settings and possible interactions between these parameters may harden (or soften) the security…

Software Engineering · Computer Science 2020-06-17 Shuvalaxmi Dass , Akbar Siami Namin

In clinical machine learning, the coexistence of multiple models with comparable performance (a manifestation of the Rashomon Effect) poses fundamental challenges for trustworthy deployment and evaluation. Small, imbalanced, and noisy…

Machine Learning · Computer Science 2026-01-13 Yuwen Zhang , Viet Tran , Paul Weng

Ensuring that large language models (LLMs) can effectively assess, detect, explain, and remediate software vulnerabilities is critical for building robust and secure software systems. We introduce VADER, a human-evaluated benchmark designed…

Cryptography and Security · Computer Science 2025-05-27 Ethan TS. Liu , Austin Wang , Spencer Mateega , Carlos Georgescu , Danny Tang

Vision Language Models (VLMs) hold great promise for streamlining labour-intensive medical imaging workflows, yet systematic security evaluations in clinical settings remain scarce. We introduce VSF--Med, an end-to-end vulnerability-scoring…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Binesh Sadanandan , Vahid Behzadan

As Deep Neural Networks (DNNs) are increasingly deployed in safety critical and privacy sensitive applications such as autonomous driving and biometric authentication, it is critical to understand the fault-tolerance nature of DNNs. Prior…

Hardware Architecture · Computer Science 2024-01-09 Abhishek Tyagi , Yiming Gan , Shaoshan Liu , Bo Yu , Paul Whatmough , Yuhao Zhu

In the rapidly evolving field of artificial intelligence (AI), the identification, documentation, and mitigation of vulnerabilities are paramount to ensuring robust and secure systems. This paper discusses the minimum elements for AI…

Cryptography and Security · Computer Science 2025-10-14 Mohamad Fazelnia , Sara Moshtari , Mehdi Mirakhorli

Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated…

Artificial Intelligence · Computer Science 2024-07-29 Sven Cattell , Avijit Ghosh , Lucie-Aimée Kaffee

Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfactuals analysis, operating via the discovery and intervention…

Machine Learning · Computer Science 2021-11-19 William Paul , Philippe Burlina

Embodied AI systems, including robots and autonomous vehicles, are increasingly integrated into real-world applications, where they encounter a range of vulnerabilities stemming from both environmental and system-level factors. These…

Cryptography and Security · Computer Science 2025-02-26 Wenpeng Xing , Minghao Li , Mohan Li , Meng Han

Recent results of machine learning for automatic vulnerability detection (ML4VD) have been very promising. Given only the source code of a function $f$, ML4VD techniques can decide if $f$ contains a security flaw with up to 70% accuracy.…

Cryptography and Security · Computer Science 2025-01-16 Niklas Risse , Marcel Böhme

As Large Language Models (LLMs) scale in size and complexity, the consequences of failures during training become increasingly severe. A major challenge arises from Silent Data Corruption (SDC): hardware-induced faults that bypass…

Machine Learning · Computer Science 2026-04-02 Anton Altenbernd , Philipp Wiesner , Odej Kao

The rise of Network Function Virtualization (NFV) has transformed network infrastructures by replacing fixed hardware with software-based Virtualized Network Functions (VNFs), enabling greater agility, scalability, and cost efficiency.…

Networking and Internet Architecture · Computer Science 2025-03-31 Mario Di Mauro , Walter Cerroni , Fabio Postiglione , Massimo Tornatore , Kishor S. Trivedi

Artificial Intelligence (AI), particularly through the advent of large-scale generative AI (GenAI) models such as Large Language Models (LLMs), has become a transformative element in contemporary technology. While these models have unlocked…

Software Engineering · Computer Science 2024-01-19 Boming Xia , Qinghua Lu , Liming Zhu , Sung Une Lee , Yue Liu , Zhenchang Xing

The rapid advancement of Artificial Intelligence (AI) has led to its integration into various areas, especially with Large Language Models (LLMs) significantly enhancing capabilities in Artificial Intelligence Generated Content (AIGC).…

Software Engineering · Computer Science 2026-01-07 Guangba Yu , Gou Tan , Haojia Huang , Zhenyu Zhang , Pengfei Chen , Roberto Natella , Zibin Zheng

Industrial components are of high importance because they control critical infrastructures that form the lifeline of modern societies. However, the rapid evolution of industrial components, together with the new paradigm of Industry 4.0,…

Cryptography and Security · Computer Science 2022-03-16 Ángel Longueira-Romero , Rosa Iglesias , Jose Luis Flores , Iñaki Garitano

This study offers an in-depth analysis of the application and implications of the National Institute of Standards and Technology's AI Risk Management Framework (NIST AI RMF) within the domain of surveillance technologies, particularly…

Computers and Society · Computer Science 2024-05-01 Nandhini Swaminathan , David Danks