Cover Image

Context manipulation attacks : Web agents are susceptible to corrupted memory

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Patlan, Atharv Singh, Hebbar, Ashwin, Viswanath, Pramod, Mittal, Prateek
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents
by: Patlan, Atharv Singh, et al.
Published: (2025)

MURMUR: Using cross-user chatter to break collaborative language agents in groups
by: Patlan, Atharv Singh, et al.
Published: (2025)

Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
by: Choudhary, Sarthak, et al.
Published: (2026)

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
by: Shen, Zeyu, et al.
Published: (2025)

Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents
by: Leong, Jun Wen
Published: (2026)

Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval
by: Wu, Hao, et al.
Published: (2025)

Are Robust LLM Fingerprints Adversarially Robust?
by: Nasery, Anshul, et al.
Published: (2025)

PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing
by: Tamboli, Dipesh, et al.
Published: (2026)

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
by: Ranganath, Suraj, et al.
Published: (2026)

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
by: Qi, Xiangyu, et al.
Published: (2024)

AgentWall: A Runtime Safety Layer for Local AI Agents
by: Aravind, Ashwin
Published: (2026)

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
by: Panda, Ashwinee, et al.
Published: (2022)

Training AI to be Loyal
by: Oh, Sewoong, et al.
Published: (2025)

AWE: Adaptive Agents for Dynamic Web Penetration Testing
by: Jaswal, Akshat Singh, et al.
Published: (2026)

OML: A Primitive for Reconciling Open Access with Owner Control in AI Model Distribution
by: Cheng, Zerui, et al.
Published: (2024)

On Evaluating the Durability of Safeguards for Open-Weight LLMs
by: Qi, Xiangyu, et al.
Published: (2024)

Privacy Auditing of Large Language Models
by: Panda, Ashwinee, et al.
Published: (2025)

MEASER: Malware embedding attacks on open-source LLMs
by: Tan, Ming, et al.
Published: (2025)

Adversarial attacks against Modern Vision-Language Models
by: La Torre, Alejandro Paredes
Published: (2026)

In-context learning for the classification of manipulation techniques in phishing emails
by: Dalmiere, Antony, et al.
Published: (2025)

Detection of ransomware attacks using federated learning based on the CNN model
by: Nguyen, Hong-Nhung, et al.
Published: (2024)

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference
by: Xiong, Zixun, et al.
Published: (2026)

A general approach to enhance the survivability of backdoor attacks by decision path coupling
by: Zhao, Yufei, et al.
Published: (2024)

Capturing the security expert knowledge in feature selection for web application attack detection
by: Riverol, Amanda, et al.
Published: (2024)

Optimized detection of cyber-attacks on IoT networks via hybrid deep learning models
by: Bensaoud, Ahmed, et al.
Published: (2025)

Mind the Web: The Security of Web Use Agents
by: Shapira, Avishag, et al.
Published: (2025)

Manipulating hidden-Markov-model inferences by corrupting batch data
by: Caballero, William N., et al.
Published: (2024)

Decoding Complexity: Intelligent Pattern Exploration with CHPDA (Context Aware Hybrid Pattern Detection Algorithm)
by: Koli, Lokesh, et al.
Published: (2025)

AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
by: Xu, Jiacen, et al.
Published: (2024)

An incremental hybrid adaptive network-based IDS in Software Defined Networks to detect stealth attacks
by: Alqahtani, Abdullah H
Published: (2024)

Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art
by: Trinh, Khoi, et al.
Published: (2026)

Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks
by: Venturi, Andrea, et al.
Published: (2024)

WIPI: A New Web Threat for LLM-Driven Web Agents
by: Wu, Fangzhou, et al.
Published: (2024)

TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks
by: Yao, Jianzhu, et al.
Published: (2025)

The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models
by: Xu, Zhiyuan, et al.
Published: (2025)

DAIRE: A lightweight AI model for real-time detection of Controller Area Network attacks in the Internet of Vehicles
by: Alam, Shahid, et al.
Published: (2026)

Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data
by: Guépin, Florent, et al.
Published: (2023)

WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents
by: Wu, Xinyi, et al.
Published: (2026)

ConfusedPilot: Confused Deputy Risks in RAG-based LLMs
by: RoyChowdhury, Ayush, et al.
Published: (2024)

Analysis of the vulnerability of machine learning regression models to adversarial attacks using data from 5G wireless networks
by: Legashev, Leonid, et al.
Published: (2025)