Aug 21·research
Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds Up Against a Large-Scale LLM Incident Corpus
The arXiv paper evaluates the robustness of the OWASP Top 10 for LLM applications using a large incident corpus from 2026. It compares the community‑expert ranking of risks against empirical incident data, finding that several high‑ranked categories under‑represent real‑world failures, suggesting a need to revise the OWASP list for LLM‑specific threats.
Source: arXiv cs.CR daily listing · Verified Aug 21
Aug 21·research
Inadvertent Context Leakage in Language Models
The authors analyse how language models unintentionally leak contextual information (e.g., prior prompts, system messages) during generation. They propose measurement methodologies and show that even well‑tuned models can expose private context, recommending stricter isolation and output filtering for privacy‑sensitive deployments.
Source: arXiv cs.CR daily listing · Verified Aug 21
Aug 21·research
Tracking the Trend in How Speech Synthesizers Deceive People
The paper tracks how speech‑synthesizer technologies have been used to deceive listeners, compiling a timeline of deep‑fake audio incidents. It quantifies the evolution of realism and identifies gaps in detection tools, calling for standardized evaluation metrics for synthetic‑voice security.
Source: arXiv cs.CR daily listing · Verified Aug 21
Aug 21·research
Auditing Cross-Lingual Fairness in Language Model Watermarking
This work introduces a benchmark for auditing cross‑lingual fairness in LLM watermarking schemes. Experiments across multiple languages reveal that existing watermark detectors exhibit variable detection rates, raising concerns about equitable enforcement of provenance verification in multilingual settings.
Source: arXiv cs.CR daily listing · Verified Aug 21
Aug 21·research
Constitutive vs. Corrective: A Causal Taxonomy of Human Runtime Involvement in AI Systems
The authors present a causal taxonomy distinguishing constitutive (built‑in) from corrective (runtime) human involvement in AI systems. By mapping intervention points, the framework helps designers decide where human oversight is most effective for safety and compliance.
Source: arXiv cs.CY daily listing · Verified Aug 21
Aug 21·research
A three-dimensional typology of agency for advanced AI systems
The paper proposes a three‑dimensional typology of agency for advanced AI systems, covering (1) decision‑making authority, (2) goal‑directedness, and (3) autonomy level. It provides illustrative cases and discusses implications for governance and liability frameworks.
Source: arXiv cs.CY daily listing · Verified Aug 21