Mohammad Allahbakhsh

Mohammad Allahbakhsh, Mohammad Hassan Bahari, Moslem Attar-Raouf

Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary for AI-enabled systems, but it is no longer sufficient. In such systems, adversaries may influence prompts, retrieved content, sensor inputs, training data, memory, tools, or human-AI interaction loops to alter system behavior without directly compromising the underlying infrastructure. This paper reframes penetration testing for AI-enabled systems as objective-driven behavioral evaluation. We define an AI-enabled system as one in which learned models materially influence behavior affecting operational outcomes, and we define AI-enabled penetration as the feasible induction of AI-governed behavior that violates one or more operational objectives under an explicit threat model. This definition preserves conventional penetration testing while extending it to adversarial pathways such as prompt injection, indirect prompt injection, data poisoning, sensor manipulation, retrieval poisoning, tool misuse, and agentic misalignment. We further propose a testing workflow that identifies operational objectives, maps AI-governed behavior, analyzes adversarial influence surfaces, defines behavioral failure criteria, executes scenario-based tests, and reports evidence linking adversarial action to objective violation. A running example involving an AI-enabled security operations center assistant illustrates how penetration may occur through behavioral influence rather than infrastructure compromise. Together, the definitions, workflow, and example provide a technical framework for evaluating adversarial success in deployed AI-enabled systems.

Florian Daniel, Pavel Kucherbaev, Cinzia Cappiello et al.

Crowdsourcing enables one to leverage on the intelligence and wisdom of potentially large groups of individuals toward solving problems. Common problems approached with crowdsourcing are labeling images, translating or transcribing text, providing opinions or ideas, and similar - all tasks that computers are not good at or where they may even fail altogether. The introduction of humans into computations and/or everyday work, however, also poses critical, novel challenges in terms of quality control, as the crowd is typically composed of people with unknown and very diverse abilities, skills, interests, personal objectives and technological resources. This survey studies quality in the context of crowdsourcing along several dimensions, so as to define and characterize it and to understand the current state of the art. Specifically, this survey derives a quality model for crowdsourcing tasks, identifies the methods and techniques that can be used to assess the attributes of the model, and the actions and strategies that help prevent and mitigate quality problems. An analysis of how these features are supported by the state of the art further identifies open issues and informs an outlook on hot future research directions.

Mohammad Allahbakhsh, Saeed Arbabi, Hamid-Reza Motahari-Nezhad et al.

The increasing application of social and human-enabled systems in people's daily life from one side and from the other side the fast growth of mobile and smart phones technologies have resulted in generating tremendous amount of data, also referred to as big data, and a need for analyzing these data, i.e., big data analytics. Recently a trend has emerged to incorporate human computing power into big data analytics to solve some shortcomings of existing big data analytics such as dealing with semi or unstructured data. Including crowd into big data analytics creates some new challenges such as security, privacy and availability issues. In this paper study hybrid human-machine big data analytics and propose a framework to study these systems from crowd involvement point of view. We identify some open issues in the area and propose a set of research directions for the future of big data analytics area.