arXiv subjects

Zikai Alex Wen

Publications and source records attributed to Zikai Alex Wen.

5 recordsLinked to original sources

arXiv2026

Forensic Schema for Psychological Manipulation in Cyber Fraud: LLM-Driven Victim Reports Analysis

Existing cybercrime classification schemas capture contact metadata and financial transactions but omit the psychological manipulation techniques perpetrators employ. We present a forensic schema (four categories, 35 questions) adding 11 manipulation indicators and cryptocurrency evidence fields to established forensic foundations. Applied to 10,994 victim reports via large language model (LLM)-driven annotation and validated against two human annotators (mean LLM-human $κ= 0.69$, matching inter-annotator $κ= 0.68$), the schema revealed a statistically distinct manipulation profile for each major fraud type (Cramer's $V$ up to $0.790$). A rationale-based evidence audit nonetheless exposed a forensic detail gap: detection of manipulation techniques was reliable, but victim narratives varied widely in the actionable detail supporting each Yes answer, and blockchain-specific identifiers were nearly absent. These findings point to AI-assisted victim intake with schema-informed follow-up questions as the most direct way to close the gap. The tiered annotation strategy also provides a reusable template for LLM-based extraction from other forensic text domains.

cs.CR↗

arXiv2026

Toward User Comprehension Supports for LLM Agent Skill Specifications

Users often interpret and select agent skills through their SKILL markdown specifications. To protect users, existing audits mainly focus on malicious or unsafe skills. We study the complementary question of whether specifications help users form bounded expectations about what a skill consumes, produces, and covers. Across 878 cybersecurity skills, we used rule-based coding to measure textual cues for four comprehension anchors, namely operational basis, output contract, boundary disclosure, and example capability demonstration. Cues for operational basis were common, but only 19.0% of specifications exhibited cues for an example task, sample, or expected outcome, and only 2.3% exhibited cues for all four anchors. We further examined a small DNS/C2 telemetry subset (n$=$6) to illustrate why missing examples may matter. Examples appeared to make first local checks easier to construct, while no-example skills typically required helper code inspection to recover command arguments or output fields. We argue that agent-skill evaluation should treat specifications as user-facing capability disclosures, not merely as containers for executable instructions.

cs.HC↗

arXiv2022

What Features Influence Impact Feel? A Study of Impact Feedback in Action Games

Making the hit effect satisfy players is a long-standing problem faced by action game designers. However, no research systematically analyzed which game design elements affect such game feel. There is not even a term to describe it. So, we propose to use impact feel to describe the player's feeling when receiving juicy impact feedback. After collecting player's comments on action games from Steam's top seller list, we trained a natural language processing (NLP) model to rank action games with their performance on impact feel. We presented a 19-feature framework of impact feedback design and examined it in the top eight and last eight games. We listed an inventory of the usage of features and found that hit stop, sound coherence, and camera control may strongly influence players' impact feel. A lack of dedicated design on one of these three features may ruin players' impact feel. Our findings may become an evaluation metric for future studies.

cs.HC↗

arXiv2022

Understanding the Challenges of Team-Based Live Streaming for First-person Shooter Games

First-person shooter (FPS) game tournaments take place across the globe. A growing number of people choose to watch FPS games online instead of attending the game events in person. However, live streaming might miss critical highlight moments in the game, including kills and tactics. We identify how and why the live streaming team fails to capture highlight moments to reduce such live streaming mistakes. We named such mistakes jarring observations. We conducted a field study of live streaming competitions of Game For Peace, a popular FPS mobile game, to summarize five typical jarring observations and identify three primary reasons that caused the issues. We further studied how to improve the live streaming system to prevent jarring observations from happening by doing semi-structured interviews with two professional streaming teams for Game For Peace. The study showed that a better system should (1) add a new sub-team role to share the director's responsibility of managing observers; (2) provide interfaces customized for three roles of live streamers in the team; (3) abstract more geographical info; (4) predict the priority of observation targets; and (5) provide non-verbal interfaces for sync-up between sub-teams. Our work provides insights for esports streaming system researchers and developers to improve the system for a smoother audience experience.

cs.HC↗

arXiv2022

New Differential Privacy Communication Pipeline and Design Framework

Organizations started to adopt differential privacy (DP) techniques hoping to persuade more users to share personal data with them. However, many users do not understand DP techniques, thus may not be willing to share. Previous research suggested that the design of DP mechanism communication could influence users' willingness to share data. Based on the prior work, we propose a new communication pipeline that starts by asking users about their privacy concerns and then provides a customized DP mechanism and communication. We also propose a design framework that systemically explores effective communication designs ranging from a text-based high-level description to a step-by-step interactive storyboard. Based on the framework, we created 17 designs and recruited five people to evaluate. Our user study showed that text-based descriptions have the highest clarity in all scenarios, while the step-by-step interactive storyboards have the potential to persuade users to trust central DP. Our future work will optimize the design and conduct a large-scale efficacy study.

cs.HC↗