ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

• URL: http://arxiv.org/abs/2604.09747v1
• Date: Fri, 10 Apr 2026 07:22:11 GMT
• Title: ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
• Abstract summary: We propose ADAM, a novel privacy attack that features data distribution estimation of a victim agent's memory.<n>Our attack substantially outperforms state-of-the-art ones, achieving up to 100% ASRs.
• Score: 18.047579533992252
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or retrieval-augmented generation (RAG) mechanisms, enabling them to further leverage prior interactions or external knowledge. However, such a design also introduces a group of critical privacy vulnerabilities: sensitive information stored in memory can be leaked through query-based attacks. Although feasible, existing attacks often achieve only limited performance, with low attack success rates (ASR). In this paper, we propose ADAM, a novel privacy attack that features data distribution estimation of a victim agent's memory and employs an entropy-guided query strategy for maximizing privacy leakage. Extensive experiments demonstrate that our attack substantially outperforms state-of-the-art ones, achieving up to 100% ASRs. These results thus underscore the urgent need for robust privacy-preserving methods for current LLM agents.

Related papers

• MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck [18.358560015688447]
  Memory-augmented agents are vulnerable to memory injection attacks.<n>We propose Memory Intent-Aware Neural Denoising(MIND), a lightweight defense framework for memory injection attack.
  arXiv  Detail & Related papers  (2026-07-30T12:11:49Z)
• MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents [74.64265314956441]
  We propose a unified black-box attack framework that poisons graph-structured external memory with coordinated text-image evidence.<n>MemVenom achieves strong end-to-end attack success with minimal impact on benign performance, reaching up to 99.15% on GPT-5-family web agents.
  arXiv  Detail & Related papers  (2026-06-09T11:53:25Z)
• Prompt-Unknown Promotion Attacks against LLM-based Sequential Recommender Systems [51.504307822017985]
  Large language model-powered sequential recommender systems (LLM-SRSs) have recently demonstrated remarkable performance.<n>This paper investigates the item promotion attack in LLM-SRSs under a more realistic setting where both the system prompt and victim model are unknown to the attacker.
  arXiv  Detail & Related papers  (2026-04-26T10:09:26Z)
• ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models [15.04025544838879]
  Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows.<n>Recent research finds that LLMs become more vulnerable because memory provides extra attack surfaces.<n>We present the first systematic study of black-box adversarial memory injection attacks that target the similarity-based retrieval mechanism.
  arXiv  Detail & Related papers  (2026-02-17T04:19:45Z)
• "Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval [44.49026453970601]
  Large language models (LLMs) have been serving as effective backbones for retrieval systems.<n>Recent studies have demonstrated that such LLM-based Retrieval is vulnerable to adversarial attacks.<n>We propose a practical black-box attack method that generates transferable injection tokens based on zero-shot surrogate LLMs.
  arXiv  Detail & Related papers  (2026-01-30T22:28:04Z)
• Searching for Privacy Risks in LLM Agents via Simulation [61.229785851581504]
  We present a search-based framework that alternates between improving attack and defense strategies through the simulation of privacy-critical agent interactions.<n>We find that attack strategies escalate from direct requests to sophisticated tactics, such as impersonation and consent forgery.<n>The discovered attacks and defenses transfer across diverse scenarios and backbone models, demonstrating strong practical utility for building privacy-aware agents.
  arXiv  Detail & Related papers  (2025-08-14T17:49:09Z)
• Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools [10.086284534400658]
  Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools.<n>We identify this as a new and stealthy threat surface that allows malicious tools to be preferentially selected by LLM agents.<n>We propose a black-box in-context learning framework that generates highly attractive but syntactically and semantically valid tool metadata.
  arXiv  Detail & Related papers  (2025-08-04T06:38:59Z)
• LLM-Based User Simulation for Low-Knowledge Shilling Attacks on Recommender Systems [28.559223475725137]
  We introduce Agent4SR, a novel framework that leverages Large Language Model (LLM)-based agents to perform low-knowledge, high-impact shilling attacks.<n>Agent4SR simulates realistic user behavior by orchestrating adversarial interactions, selecting items, assigning ratings, and crafting reviews, while maintaining behavioral plausibility.<n>Our findings reveal a new class of emergent threats posed by LLM-driven agents, underscoring the urgent need for enhanced defenses in recommender systems.
  arXiv  Detail & Related papers  (2025-05-18T04:40:34Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Memory Injection Attacks on LLM Agents via Query-Only Interaction [49.14715983268449]
  We propose a novel Memory INJection Attack, MINJA, without assuming that the attacker can directly modify the memory bank of the agent.<n>The attacker injects malicious records into the memory bank by only interacting with the agent via queries and output observations.<n> MINJA enables any user to influence agent memory, highlighting the risk.
  arXiv  Detail & Related papers  (2025-03-05T17:53:24Z)
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases [73.04652687616286]
  We propose AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance.
  arXiv  Detail & Related papers  (2024-07-17T17:59:47Z)
• "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [74.05368440735468]
  Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases.
  arXiv  Detail & Related papers  (2024-06-26T05:36:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.