323

arXiv:2512.14860v1 Announce Type: new
Abstract: Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, …
230

arXiv:2512.14778v1 Announce Type: new
Abstract: This study investigates the key skills and competencies needed by new cybersecurity graduates in the Philippines for entry-level positions. Using a descriptive cross-sectional research design, it combines analysis of job listings from Philippine onlin…
213

arXiv:2511.17874v2 Announce Type: replace
Abstract: LLM applications (i.e., LLM apps) leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional application development. While the increasing prevalence of LLM-powered applications provides users…
234

Infamous hacking group ShinyHunters has claimed responsibility for the theft of a large dataset tied to Pornhub Premium users, threatening to leak or sell the information unless the company pays a ransom. The hack of PornHub was first revealed by the adult video website on Dec. 12, which it describe…
111

arXiv:2512.13767v1 Announce Type: new
Abstract: Cyber-physical systems (CPS) such as unmanned aerial vehicles are vulnerable to slow degradation that develops without causing immediate or obvious failures. Small sensor biases or timing irregularities can accumulate over time, gradually reducing sta…
119

arXiv:2512.14376v1 Announce Type: new
Abstract: WebAssembly (Wasm) has risen as a widely used technology to distribute computing workloads on different platforms. The platform independence offered through Wasm makes it an attractive solution for many different applications that can run on disparate…