Threat

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 38

All topics

An LLM-powered Agent Framework for Heterogeneous Evacuation Behavior Modeling under a Moving Threat in a Public Plaza
Sep 29, 2026Jian Ma, Runxin Yu, Tianyu Tang +1Agent-Based Model Threat
School of Transportation and Logistics, Southwest Jiaotong University, Chengdu, 610031, China · Fujian Police College, Fuzhou, 350007, China
XPhysICS: Cross-Physical-Domain Threat Grounding for Industrial Control Systems Security
Sep 25, 2026Sangshin Park, Jainta Paul, Lawrence Ponce +3Cyber-Physical System Threat
University of Utah, Salt Lake City, Utah, USA · Kahlert School of Computing, University of Utah, Salt Lake City, Utah, USA
Unifying Models of Intergroup Hostility in Online Discourse
Sep 17, 2026Patrick Gerard, Julia Mendelsohn, Kristina LermanHate Speech Ideology
Information Sciences Institute, University of Southern California · University of Maryland · Indiana University, Bloomington
Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures
Sep 14, 2026Danny Wood, James StringerAttacker Large Language Model Steganography
Fuzzy Labs
AI Persuasion as a Threat to Human Control
Sep 13, 2026Joshua Levy, Mick Yang, Kellin PelrinePersuasion Artificial Intelligence Safety
When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems
Aug 7, 2026Zhen Huang, Zhihuang Liu, Weijia Shi +3Multi-Robot Systems Multi-Agent Large Language Model Systems
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence
Aug 7, 2026Jiayun Zhang, Junshen Xu, Zejun Xie +1Cyber Threat Intelligence Threat
Amazon Web Services New York, New York, USA · Amazon Web Services Boston, Massachusetts, USA · Rutgers University Piscataway, New Jersey, USA
Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation
Jul 30, 2026Fazhong Liu, Zhuoyan Chen, Haozhen Tan +3World Models Realistic Threat Model
ThreatForest: Multi-Agent Attack Tree Generation with Pluggable TTP Framework Mapping
Jul 29, 2026Cristian Leo, Anton Dykyi, Danny Cortegaca +2Realistic Threat Model Threat
Amazon Web Services, Inc., 410 Terry Avenue North, Seattle, WA, 98109, United States · Amazon Web Services EMEA SARL, UK Branch, 1 Principal Place, Worship Street, London, EC2A 2FA, United Kingdom
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
Jul 27, 2026Xi Li, Shu Zhao, Xiaohan Zou +6Large Language Model Safety Multimodal Large Language Models
University of Alabama at Birmingham · NVIDIA · Penn State University +4
Salience Induction against Multi-Hop RAG Agents: Threat and Defense
Jul 20, 2026Xingfu Zhou, Pengfei Wang, Yuan Zhou +2LLM Defense Mechanisms Multi-Hop Reasoning
National University of Defense Technology China
SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification
Jul 10, 2026Ivan Alejandro Montoya Sanchez, Anantaa Kotal, Aritran PiplaiCybersecurity Threat
The University of Texas at El Paso
Idiobionics: The Unification of Privacy and Intelligent Robotic Prostheses
Jul 8, 2026Kwesi Afari Darfoor, Patrick M. Pilarski, Bailey KacsmarAbox Abduction Problem Privacy
Department of Computing Science, University of Alberta, Edmonton, Canada · Alberta Machine Intelligence Institute (Amii), Edmonton, Canada · Department of Medicine, University of Alberta, Edmonton, Canada
Agent Data Injection Attacks are Realistic Threats to AI Agents
Jul 6, 2026Woohyuk Choi, Juhee Kim, Taehyun Kang +3Instruction Injection Attacks Artificial Intelligence Agents
Seoul National University · Largosoft · University of Illinois Urbana-Champaign
Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata Privacy
Jun 26, 2026Oscar Thees, Roman Müller, Matthias TemplRe-Identification Mobility
University of Applied Sciences and Arts Northwestern Switzerland (FHNW), Riggenbachstrasse 16, 4600 Olten, Switzerland
Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions
Jun 25, 2026Gerhard Backfried, Christian Schmidt, Diego Pilutti +1Large Language Model Safety Threat
HENSOLDT Austria, Vienna, Austria · Austrian Ministry of Defence, Vienna, Austria
Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News
Jun 25, 2026Raven Adam, David Maier, Marie KoglerTask Framing Headlines
University of Graz, Austria · Technical University of Graz, Austria
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Jun 22, 2026Ruixiao Lin, Xinhao Deng, Qingming Li +12Cyberattacks Threat
1Zhejiang University · 2Ant Group · 3Tsinghua University +3
AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework
Jun 16, 2026Inderjeet Singh, Haitham Mahmoud, Andrés MurilloSandbox Artificial Intelligence Risk
Fujitsu Research of Europe, United Kingdom
A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framework Development
Jun 12, 2026Ahmed Mohammed Almalki, Mehedi MasudSecurity Evaluation Production Agentic Systems
Department of Computer Science College of Computers and Information Technology Taif University, KSA
AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions
Jun 7, 2026Chenglin YangAI Trustworthiness Threat
Independent Researcher
Path Planning Using Deep Deterministic Policy Gradient: A Reinforcement Learning Approach
Jun 5, 2026Qiang Le, Yaguang Yang, Isaac E. WeintraubPath Planning Path
Hampton University, Hampton, VA 23669, USA · Air Force Research Laboratory, Wright-Patterson AFB, OH 45433, USA
Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing
Jun 1, 2026Alexandre Cristovão MaioranoAttacker Large Language Model LLM Defense Mechanisms
Lumytics
Triaging Threats to Specialized Guardrails
May 29, 2026Wenjie Jacky Mo, Xiaofei Wen, Rui Cai +6Guardrail Large Language Model Safety
University of California, Davis
Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem
May 27, 2026Luca Beurer-Kellner, Aleksei Kudrinskii, Marco Milanta +3Malicious Agents Reusable Agent Skills
1Snyk
Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
May 24, 2026Wenjuan Li, Yitao Liu, Runze Chen +1Large Language Model Fine-Tuning Model Fine-Tuning
Hangzhou Normal University, No. 2318, Yuhangtang Rd, Hangzhou, 311121, Zhejiang, China · Zhejiang University, No. 866 Yuhangtang Rd, Hangzhou, 2026 310058, Zhejiang, China · China Mobile (Zhejiang) Innovation Research Institute Co., Ltd., No. 77 Gaoxin 7th Rd, China Mobile Zhejiang Information and Communication Industrial Park, Hangzhou, 311200, Zhejiang, China +1
Targeted Downstream-Agnostic Attack
May 19, 2026Zhuxin Lei, Ziyuan Yang, Yi ZhangBlack-Box Adversarial Attacks White-Box Spectral-Subspace-Guided Attack
College of Computer Science, Sichuan University, Chengdu, China
Threats to Arabic Handwriting Recognition: Investigating Black-Box Adversarial Attacks on embedded ConvNet models
May 18, 2026Mohsine EL Khayati, Abdelillah Semma, Abdelaziz Courr +1Handwritten Text Recognition Black-Box Adversarial Attacks
Systems theory and informatics laboratory Moulay Ismail University of Meknes Meknes, Morocco · Department of Computer Science EST of Sidi Bennour Chouaib Doukkali University Eljadida, Morocco · Faculty of Education Sciences University Mohammed V Rabat, Morocco +1
The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort
May 16, 2026Aleksandr ChurilovLarge Language Model Hallucination Citation Hallucination
Independent Researcher
The Deepfakes We Missed: We Built Detectors for a Threat That Didn't Arrive
May 12, 2026Shaina RazaDeepfake Detection Threat
Vector Institute for Artificial Intelligence, Toronto, Canada.
ThreatCore: A Benchmark for Explicit and Implicit Threat Detection
May 11, 2026Davide Bruni, Carlo Bardazzi, Maurizio TesconiHate Speech Detection Threat
Computer Science Department, University of Pisa, Italy · Institute of Informatics and Telematics, National Research Council, Italy
The Insurability Frontier of AI Risk: Mapping Threats to Affirmative Coverage, Silent Exposures, and Exclusions
May 6, 2026Alex Leung, Rex Zhang, Ervin Ling +2Insurance Artificial Intelligence Risk
AIFT
Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities
May 5, 2026Devon Jarvis, Richard Klein, Benjamin Rosman +2Large Language Models Fail Collapse
School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa · Machine Intelligence and Neural Discovery Institute, University of the Witwatersrand, Johannesburg, South Africa · Data Science and AI, Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg
From Prompt to Physical Actuation: Holistic Threat Modeling of LLM-Enabled Robotic Systems
Apr 29, 2026Neha Nagaraja, Hayretdin Bahsi, Carlo R. da CunhaRealistic Threat Model Threat
School of Informatics, Computing, and Cyber Systems, Northern Arizona University, Flagstaff, USA · Department of Software Science, Tallinn University of Technology, Tallinn, Estonia
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
Apr 26, 2026Qi Li, Bo Yin, Weiqi Huang +6Diffusion-Based Vision-Language-Actions Embodied Artificial Intelligence
National University of Singapore · Peking University · Monash University
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
Apr 25, 2026Kexin ChuThreat Agentic
School of Computing, University of Connecticut
Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps
Apr 21, 2026Alankrit Chona, Igor Kozlov, Ambuj KumarSecurity Evaluation Threat
Simbian AI
Flocking phase transition and threat responses in bio-inspired autonomous drone swarms
Dec 24, 2025Matthieu Verdoucq, Dari Trendafilov, Clément Sire +3Unmanned Aerial Vehicle Swarms Swarms
Ecole Nationale de l’Aviation Civile, Université de Toulouse, France · Centre de Recherches sur la Cognition Animale, Centre de Biologie Intégrative (CBI), Centre National de la Recherche Scientifique (CNRS) & Université de Toulouse – Paul Sabatier, France · Laboratoire de Physique Théorique, CNRS & Université de Toulouse – Paul Sabatier, France

Sep 29, 2026, physics.soc-phJ/K move · Enter open · S save

An LLM-powered Agent Framework for Heterogeneous Evacuation Behavior Modeling under a Moving Threat in a Public Plaza

Jian Ma, Runxin Yu, Tianyu Tang, Xiaolian Li

School of Transportation and Logistics, Southwest Jiaotong University, Chengdu, 610031, China · Fujian Police College, Fuzhou, 350007, China

Agent-Based Model Threat Decisions

Open paper AskPDF arXiv

Modeling heterogeneous evacuation behavior under a moving threat is difficult because human perception, memory, and evidence evaluation are not well captured by fixed rules. We propose a novel LLM-powered agent-based framework to represent these internal decision processes. Each pedestrian agent perceives a private symbolic ASCII view, maintains a Memory-based Knowledge Graph derived solely from individual observations, and makes decisions through persona-conditioned prompts under a common sampling configuration. A compressed decision context with stateless memory preserves trial-and-error experience across turns while excluding reasoning traces, and a validation engine separates behavioral choice from physical feasibility by executing routes only over observed terrain. We evaluated eight personality compositions in eight paired randomized blocks within a simulated public plaza. Usable-exit knowledge was strongly associated with evacuation success: 89.5% of agents possessing such knowledge evacuated, compared with 1.05% of those without it. Personality compositions also differed in their evaluation of remembered threat evidence: the proportion of danger assessments varied by 0.265, while high-urgency, low-directness decisions ranged from 11.41% to 34.33%. After direct threat sightings, responses converged, with 99.6% of assessments classifying the situation as dangerous. Movement was selected in 99.8% of decisions. Overall, evacuation outcomes were strongly associated with information access, while evacuation time was jointly associated with spatial geometry, information, and affect. The framework provides an auditable approach to generating endogenous behavioral heterogeneity through persona-conditioned LLM agents in crowd-evacuation simulations.

Momentum

Related topics

Latest papers 38