Cover Image

Hallucination as Exploit: Evidence-Carrying Multimodal Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Guijia, Zheng, Hao, Yang, Harry
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AI Agent Smart Contract Exploit Generation
by: Gervais, Arthur, et al.
Published: (2025)

When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks
by: Cai, Ziwen, et al.
Published: (2026)

Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents
by: Jiang, Linxi, et al.
Published: (2026)

LLM Agents can Autonomously Exploit One-day Vulnerabilities
by: Fang, Richard, et al.
Published: (2024)

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
by: Liu, Zesen, et al.
Published: (2025)

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
by: Lee, Seunghyun, et al.
Published: (2026)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
by: Zou, Wei, et al.
Published: (2026)

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
by: Ferrag, Mohamed Amine, et al.
Published: (2025)

CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents
by: Emerson, Harry, et al.
Published: (2024)

DECEPTICON: How Dark Patterns Manipulate Web Agents
by: Cuvin, Phil, et al.
Published: (2025)

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
by: Wen, Ruoyao, et al.
Published: (2026)

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
by: Li, Yanzeng, et al.
Published: (2025)

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
by: Yan, Lu, et al.
Published: (2025)

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
by: Li, Yanjie, et al.
Published: (2025)

LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks
by: Zhang, Qingzhao, et al.
Published: (2024)

AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents
by: Zheng, Ye, et al.
Published: (2025)

CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models
by: Min, Nay Myat, et al.
Published: (2026)

Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior
by: Lian, Zhuotao, et al.
Published: (2025)

Hallucination-Resistant Security Planning with a Large Language Model
by: Hammar, Kim, et al.
Published: (2026)

MTRE: Multi-Token Reliability Estimation for Hallucination Detection in VLMs
by: Zollicoffer, Geigh, et al.
Published: (2025)

SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents
by: Liang, Siyuan, et al.
Published: (2025)

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
by: Wang, Zhun, et al.
Published: (2026)

LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits
by: Badhe, Sanket
Published: (2025)

Security of AI Agents
by: He, Yifeng, et al.
Published: (2024)

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
by: Zheng, Baolin, et al.
Published: (2025)

AgentMark: Utility-Preserving Behavioral Watermarking for Agents
by: Huang, Kaibo, et al.
Published: (2026)

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
by: Yang, Chenglin
Published: (2026)

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations
by: Collu, Matteo Gioele, et al.
Published: (2026)

"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models
by: Tan, Zhen, et al.
Published: (2024)

Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations
by: Wong, Ryan, et al.
Published: (2025)

Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection
by: Song, Chengyu, et al.
Published: (2024)

MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation
by: Zhao, Yizhe, et al.
Published: (2026)

Good News for Script Kiddies? Evaluating Large Language Models for Automated Exploit Generation
by: Jin, David, et al.
Published: (2025)

Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders
by: Noever, David, et al.
Published: (2024)

Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems
by: Rathnasuriya, Ravishka, et al.
Published: (2025)

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs
by: Xu, Wenzhuo, et al.
Published: (2026)

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
by: Wang, Kun, et al.
Published: (2026)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
by: Ning, Liang-bo, et al.
Published: (2025)

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
by: Chen, Yanzuo, et al.
Published: (2023)

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
by: Ding, Ruyi, et al.
Published: (2025)