Buchumschlag

StruPhantom: Evolutionary Injection Attacks on Black-Box Tabular Agents Powered by Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Feng, Yang, Pan, Xudong
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models
von: Yang, Yiqi, et al.
Veröffentlicht: (2024)

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
von: Wang, Shuqiang, et al.
Veröffentlicht: (2026)

SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection
von: Feng, Yang, et al.
Veröffentlicht: (2025)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
von: Domico, Kyle, et al.
Veröffentlicht: (2025)

AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
von: Wang, Zhun, et al.
Veröffentlicht: (2025)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
von: Park, Junyoung, et al.
Veröffentlicht: (2026)

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

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
von: Wang, Haowei, et al.
Veröffentlicht: (2025)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
von: Yu, Miao, et al.
Veröffentlicht: (2024)

Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models
von: Chen, Zhuo, et al.
Veröffentlicht: (2024)

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search
von: Shen, Yulin, et al.
Veröffentlicht: (2026)

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection
von: Li, Zongze, et al.
Veröffentlicht: (2025)

Prompt Injection Attacks on Large Language Models in Oncology
von: Clusmann, Jan, et al.
Veröffentlicht: (2024)

PAL: Proxy-Guided Black-Box Attack on Large Language Models
von: Sitawarin, Chawin, et al.
Veröffentlicht: (2024)

Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models
von: Li, Yakai, et al.
Veröffentlicht: (2025)

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
von: Zhu, Kaijie, et al.
Veröffentlicht: (2025)

On Jailbreaking Quantized Language Models Through Fault Injection Attacks
von: Zahran, Noureldin, et al.
Veröffentlicht: (2025)

Securing AI Agents Against Prompt Injection Attacks
von: Ramakrishnan, Badrinath, et al.
Veröffentlicht: (2025)

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
von: Yin, Jinhua, et al.
Veröffentlicht: (2025)

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
von: Cheng, Ruoxi, et al.
Veröffentlicht: (2024)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
von: Wang, Libo
Veröffentlicht: (2024)

Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS
von: Ennaji, Sabrine, et al.
Veröffentlicht: (2025)

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
von: Lv, Peizhuo, et al.
Veröffentlicht: (2025)

Goal-guided Generative Prompt Injection Attack on Large Language Models
von: Zhang, Chong, et al.
Veröffentlicht: (2024)

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
von: Cao, Tri, et al.
Veröffentlicht: (2025)

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt
von: Wang, Zhilong, et al.
Veröffentlicht: (2025)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
von: Evtimov, Ivan, et al.
Veröffentlicht: (2025)

Evaluation of Prompt Injection Defenses in Large Language Models
von: Deep, Priyal, et al.
Veröffentlicht: (2026)

Review-Incorporated Model-Agnostic Profile Injection Attacks on Recommender Systems
von: Yang, Shiyi, et al.
Veröffentlicht: (2024)

How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World
von: Panebianco, Francesco, et al.
Veröffentlicht: (2025)

Optimization-based Prompt Injection Attack to LLM-as-a-Judge
von: Shi, Jiawen, et al.
Veröffentlicht: (2024)

Hide and Seek: Fingerprinting Large Language Models with Evolutionary Learning
von: Iourovitski, Dmitri, et al.
Veröffentlicht: (2024)

Behavior-Aware and Generalizable Defense Against Black-Box Adversarial Attacks for ML-Based IDS
von: Ennaji, Sabrine, et al.
Veröffentlicht: (2025)

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
von: Guan, Zelin, et al.
Veröffentlicht: (2026)

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
von: Qiu, Huming, et al.
Veröffentlicht: (2023)

SurvAttack: Black-Box Attack On Survival Models through Ontology-Informed EHR Perturbation
von: Kerdabadi, Mohsen Nayebi, et al.
Veröffentlicht: (2024)

Comparative Analysis of Black-Box and White-Box Machine Learning Model in Phishing Detection
von: Fajar, Abdullah, et al.
Veröffentlicht: (2024)

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
von: Li, Jie, et al.
Veröffentlicht: (2024)

Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
von: Lu, Yifan, et al.
Veröffentlicht: (2023)

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
von: Yang, Fan
Veröffentlicht: (2025)