Hijacking

Follow this topic Ask about this topic

Momentum

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

Jul 13Week of Sep 28

Latest papers 29

All topics

Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
Sep 23, 2026Tiantong Wu, Wei Yang Bryan LimIndirect Prompt Injection Hijacking
Nanyang Technological University Singapore
Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models
Sep 23, 2026Kian Shamsaie, Iman ModarressiFull-Duplex Speech Models Hijacking
People Make Things
A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
Sep 22, 2026Laizhen Li, Xuan Wang, Peicheng Zhao +4Model Context Protocol Hijacking
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Nanyang Technological University +3
DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents
Sep 12, 2026Asif Pinjari, Mithun Paul Saint-GermainPrompt-Injection Detectors Attacker Large Language Model
School of Informatics, Computing, and Cyber Systems Northern Arizona University Flagstaff, AZ, USA
AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents
Sep 10, 2026Zhihao Liu, Hongyu Sun, Zhiyuan Fu +7Computer-Use Agents Instruction Injection Attacks
Hainan University, Hainan 570228, China · University of Chinese Academy of Sciences National Computer Network Intrusion Protection Center, Beijing 101408, China · School of Computing and Communications, Lancaster University, Lancaster, United Kingdom
Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation
Aug 13, 2026Rana Muhammad Ahmed, Sabahat AbbasSecurity Evaluation Model Auditing
Department of Computer Science, Bahria University, Islamabad, Pakistan
Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
Aug 12, 2026Junliang Liu, Ruoyu Li, Wenxin Tang +4Hijacking
School of Computer Science and Software Engineering, Shenzhen University · The Chinese University of Hong Kong · The Chinese University of Hong Kong, Shenzhen
CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal
Aug 6, 2026Arash Vashagh, Yasmin VashaghCells Cohort
Faculty of Computer Science, University of New Brunswick, Fredericton, New Brunswick E3B 5A3, Canada · Farzanegan Amin 2 High School, Isfahan, Iran
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
Jul 28, 2026Yu Yan, Jiahao Chen, Siqi Lu +6Large Language Model Decisions Attacker Large Language Model
College of Computer Science and Technology, Zhejiang University · Henan Key Laboratory of Network Cryptography Technology, Information Engineering University · State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences
HijackKV: New Threat in Position-Independent KV Cache Reuse
Jul 22, 2026Yichi Zhang, Zhiqi Wang, Huan Zhang +1Key-Value Cache Cache
The Pennsylvania State University · University of Illinois Urbana-Champaign
MemPoison: Bypassing Selective Memory Mechanisms to Plant Backdoors in LLM Agents
May 28, 2026Hongtao Wang, Se Yang, Yu Chen +1Poisoning Attacker Large Language Model
North China Electric Power University China · Tencent China · Tsinghua University China
Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking
May 27, 2026Ziyang You, Huilong He, Xiaoke Yang +1Large Language Model Watermarks Attacker Large Language Model
Fujian Provincial Key Laboratory of Automotive Electronics and Electric Drive, School of Electronic, Electrical and Physics, Fujian University of Technology, Fuzhou 350118, China · School of Humanities, Fujian University of Technology, Fuzhou 350118, China · Institute of Applied Physics and Materials Engineering, University of Macau, Macau 999078, China
VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
May 27, 2026Jiyuan Fu, Kaixun Jiang, Jingkai Jia +7Hijacking Proprioception
Fudan University · The Hong Kong Polytechnic University
SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
May 27, 2026Jiachen QianAgentic Retrieval-Augmented Generation Systems Poisoning
City University of Hong Kong · Hong Kong, Hong Kong
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
May 25, 2026Jingwei Sun, Jianing Zhu, Yuanyi Li +3Computer-Use Agents Hijacking
TMLR Group, Hong Kong Baptist University · The University of Texas at Austin · Sydney AI Centre, The University of Sydney +1
IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization
May 23, 2026Zixuan Chen, Jiaxiang Chen, Li Luo +4Indirect Prompt Injection Large Language Model Agents
1Shanghai Jiao Tong University · 2The University of Hong Kong
Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content
May 23, 2026Rohan Pandey, Archit BhujangIndirect Prompt Injection Attacker Large Language Model
DigitalOcean · Arizona State University
The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
May 17, 2026Qiqi Liu, Thorsten Holz, Shilin Ye +1Attack-Success Rate Hijacking
University of Chinese Academy of Sciences · Max Planck Institute for Security and Privacy · Henan Yinzhu Safety Technology Co., Ltd. +1
Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models
May 17, 2026Zhiqiang Wang, Dongrui Liu, Yan Li +4Hijacking Responses
Hong Kong University of Science and Technology · Shanghai Jiao Tong University · Beihang University
Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution
May 11, 2026Neil Fendley, Zhengyu Liu, Aonan Guan +2Agentic Workflows Hijacking
Johns Hopkins University Maryland, USA · Wyze Labs Washington, USA
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
May 11, 2026Yangneng Chen, Junlin Li, Weijun Yao +4Long Visual-Token Sequences Large Language Model Hallucination
1Harbin Institute of Technology (Shenzhen), China · 2Huawei Technologies Co., Ltd. · 3The Hong Kong Polytechnic University +1
Seed Hijacking of LLM Sampling and Quantum Random Number Defense
May 8, 2026Ziyang You, Xiaoke Yang, Zhanling Fan +3Attacker Large Language Model Random
School of Electronic, Electrical and Physics, Fujian University of Technology, Fuzhou 350118, China · School of Humanities, Fujian University of Technology, Fuzhou 350118, China · Department of Investigation, Fujian Police College, Fuzhou 350007, China +1
WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
May 8, 2026Zhichao Liu, Wenbo Pan, Haining Yu +3Hijacking Browser Agent
Harbin Institute of Technology · City University of Hong Kong · City University of Macau
RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
May 1, 2026Zhiyuan Xu, Joseph Gardiner, Sana Belguith +1Jailbreak Success Rates Mixture-Of-Experts
University of Bristol Bristol, United Kingdom
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
Apr 30, 2026Zi Li, Tian Zhou, Wenze Li +3Attacker Large Language Model Large Language Model Fine-Tuning
Nanjing University
Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
Apr 22, 2026Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis +2Attacker Large Language Model Hijacking
IBM Research Europe · Trinity College Dublin · Imperial College London +1
Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
Apr 20, 2026Wenpeng XuGraphical User Interface Agents Cyberattacks
University of California, San Diego
Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
Apr 16, 2026Meng Chen, Kun Wang, Li Lu +2Large Audio Language Models Hijacking
The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security · National University of Singapore +1
Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution
Apr 11, 2026Robert DilworthStylometric Anonymization
Department of Computer Science and Engineering, Mississippi State University, Mississippi State, Mississippi, USA

Sep 23, 2026, cs.CRJ/K move · Enter open · S save

Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions

Tiantong Wu, Wei Yang Bryan Lim

Nanyang Technological University Singapore

Indirect Prompt Injection Hijacking Probabilistic Model Schema

Open paper AskPDF arXiv

Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-generative decision model, using 510 reconstructed InjecAgent cases. Malicious content shifts action probabilities but rarely causes Jev to select the attacker's target. Override markers reduce this influence, while claims of contextual relatedness have small effects. Adaptive attacks using score feedback double the mean highest attacker-target probability found during optimization, while success on fresh validation calls rises from 1.8% to 3.5%. Exploratory analysis links these successes to small initial decision margins or greater attacker control over the observation. Together, these findings show that schema-defined outputs change but do not eliminate prompt-injection risk, highlighting the need to evaluate how untrusted content influences choices within the allowed action set.

Momentum

Related topics

Latest papers 29