Exploiting Web Search Tools of AI Agents for Data Exfiltration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rall, Dennis, Bauer, Bernhard, Mittal, Mohit, Fraunholz, Thomas
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language 68T50, 68T0 F.2.2; I.2.7; K.6.5
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
by: Dang, Kieu, et al.
Published: (2025)

Tool Receipts, Not Zero-Knowledge Proofs: Practical Hallucination Detection for AI Agents
by: Basu, Abhinaba
Published: (2026)

AVEC: Bootstrapping Privacy for Local LLMs
by: Gaikwad, Madhava
Published: (2025)

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
by: Hill, Brennen, et al.
Published: (2025)

LegalGuardian: A Privacy-Preserving Framework for Secure Integration of Large Language Models in Legal Practice
by: Demir, M. Mikail, et al.
Published: (2025)

BreakFun: Jailbreaking LLMs via Schema Exploitation
by: Oskooei, Amirkia Rafiei, et al.
Published: (2025)

Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks
by: Merves, Tyler H., et al.
Published: (2026)

A Method for Quantifying Human Risk and a Blueprint for LLM Integration
by: Canale, Giuseppe
Published: (2025)

Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA
by: Badshah, Sher, et al.
Published: (2024)

Detecting Sleeper Agents in Large Language Models via Semantic Drift Analysis
by: Zanbaghi, Shahin, et al.
Published: (2025)

Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility
by: Engelberg, Gal, et al.
Published: (2026)

MarkLLM: An Open-Source Toolkit for LLM Watermarking
by: Pan, Leyi, et al.
Published: (2024)

A Semantic Invariant Robust Watermark for Large Language Models
by: Liu, Aiwei, et al.
Published: (2023)

Can Watermarked LLMs be Identified by Users via Crafted Prompts?
by: Liu, Aiwei, et al.
Published: (2024)

Hardening x402: PII-Safe Agentic Payments via Pre-Execution Metadata Filtering
by: Stantchev, Vladimir
Published: (2026)

On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection
by: Schappacher-Tilp, Gudrun, et al.
Published: (2026)

Exploratory Analysis of Cyberattack Patterns on E-Commerce Platforms Using Statistical Methods
by: Adeniya, Fatimo Adenike
Published: (2025)

Agentic Artificial Intelligence for Ethical Cybersecurity in Uganda: A Reinforcement Learning Framework for Threat Detection in Resource-Constrained Environments
by: Adabara, Ibrahim, et al.
Published: (2025)

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs
by: Bahar, Atmane Ayoub Mansour, et al.
Published: (2024)

MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
by: Pan, Leyi, et al.
Published: (2025)

How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks
by: Wang, Yanshu, et al.
Published: (2026)

RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection
by: Buonocore, Tommaso Mario, et al.
Published: (2025)

Generative AI Models: Opportunities and Risks for Industry and Authorities
by: Alt, Tobias, et al.
Published: (2024)

Watermarking for AI Content Detection: A Review on Text, Visual, and Audio Modalities
by: Cao, Lele
Published: (2025)

Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible
by: Zhao, Lepeng, et al.
Published: (2026)

Vibe-Creation: The Epistemology of Human-AI Emergent Cognition
by: Levin, Ilya
Published: (2026)

h4rm3l: A language for Composable Jailbreak Attack Synthesis
by: Doumbouya, Moussa Koulako Bala, et al.
Published: (2024)

SCARA: A Semantics-Constrained Autonomous Remediation Agent for Opaque Industrial Software Vulnerabilities
by: Ning, Bowei, et al.
Published: (2026)

Monotonicity as an Architectural Bias for Robust Language Models
by: Cooper, Patrick, et al.
Published: (2026)

Revisiting Third-Party Library Detection: A Ground Truth Dataset and Its Implications Across Security Tasks
by: Gu, Jintao, et al.
Published: (2025)

CyberAId: AI-Driven Cybersecurity for Financial Service Providers
by: Fatouros, George, et al.
Published: (2026)

Approaching I/O-optimality for Approximate Attention
by: Papp, Pál András, et al.
Published: (2026)

PennyCoder: Efficient Domain-Specific LLMs for PennyLane-Based Quantum Code Generation
by: Basit, Abdul, et al.
Published: (2025)

Semantically Guided Adversarial Testing of Vision Models Using Language Models
by: Filus, Katarzyna, et al.
Published: (2025)

Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers
by: Wang, Haochuan Kevin, et al.
Published: (2026)

Dark LLMs: The Growing Threat of Unaligned AI Models
by: Fire, Michael, et al.
Published: (2025)

Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
by: Alam, Firoj, et al.
Published: (2026)

LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target
by: Hasan, Md Arid, et al.
Published: (2025)

PropXplain: Can LLMs Enable Explainable Propaganda Detection?
by: Hasanain, Maram, et al.
Published: (2025)

Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches
by: De Mel, Yomal, et al.
Published: (2024)