Workshop on LLM Assisted Security and Trust Exploration (LAST-X) 2026 Accepted Papers

View the detailed program page to learn when each paper will be presented during the upcoming event.

A Temporal Paradox in Software Vulnerability Prioritization: Why Do Large Language Models Perform Better Post-Knowledge Cutoff Date?

Osama Al Haddad (Macquarie University, Sydney, Australia), Muhammad Ikram (Macquarie University, Sydney, Australia), Young Choon Lee (Macquarie University, Sydney, Australia), Muhammad Ejaz Ahmed (Data61 CSIRO, Sydney, Australia)

Auditable LLM Arbiter for DeFi Security: A Hybrid Graph-of-Thoughts Approach to Intent–Transaction Alignment

Duanyi Yao (Navalabs), Siddhartha Jagannath (Navalabs), Baltasar Aroso (Navalabs), Vyas Krishnan (Navalabs), Ding Zhao (Navalabs)

AWE: Adaptive Agents for Dynamic Web Penetration Testing

Akshat Singh Jaswal (Stux Labs), Ashish Baghel (Stux Labs)

Context Relay for Long-Running Penetration-Testing Agents

Marius Vangeli (KTH Royal Institute of Technology, Sweden), Joel Brynielsson (KTH Royal Institute of Technology, Sweden and FOI Swedish Defence Research Agency, Sweden), Mika Cohen (KTH Royal Institute of Technology, Sweden and FOI Swedish Defence Research Agency, Sweden), Farzad Kamrani (FOI Swedish Defence Research Agency, Sweden)

HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation

Yonatan Gizachew Achamyeleh (University of California, Irvine), Harsh Thomare (University of California, Irvine), Mohammad Abdullah Al Faruque (University of California, Irvine)

Local LLMs for NL2Bash: A Large-Scale Open-Source Model Evaluation for Bash Command Generation

Jef Jacobs (DistriNet, KU Leuven), Jorn Lapon (DistriNet, KU Leuven), Vincent Naessens (DistriNet, KU Leuven)

On the Difficulty of Selecting Few-Shot Examples for Effective LLM-based Vulnerability Detection

Md Abdul Hannan (Colorado State University), Ronghao Ni (Carnegie Mellon University), Chi Zhang (Carnegie Mellon University), Limin Jia (Carnegie Mellon University), Ravi Mangal (Colorado State University), Corina S. Pasareanu (Carnegie Mellon University)

PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM

Gautam Savaliya (Deggendorf Institute of Technology, Germany), Robert Aufschlager (Deggendorf Institute of Technology, Germany), Abhishek Subedi (Deggendorf Institute of Technology, Germany), Michael Heigl (Deggendorf Institute of Technology, Germany), Martin Schramm (Deggendorf Institute of Technology, Germany)

Proactive Hardening of LLM Defenses with HASTE

Henry Chen (Palo Alto Networks), Victor Aranda (Palo Alto Networks), Samarth Keshari (Palo Alto Networks), Ryan Heartfield (Palo Alto Networks), Nicole Nichols (Palo Alto Networks)

Vibenix: An AI Assistant for Software Packaging with Nix

Martin Schwaighofer (Johannes Kepler University Linz), Martim Monis (INESC-ID and IST, University of Lisbon), Nuno Saavedra (INESC-ID and IST, University of Lisbon), Joao F. Ferreira (INESC-ID and Faculty of Engineering, University of Porto), Rene Mayrhofer (Johannes Kepler University Linz)