Cover Image

Memory-Induced Tool-Drift in LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dabas, Mahavir, Jeong, Jihyun, Jin, Ming, Jia, Ruoxi
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
by: Li, Songze, et al.
Published: (2024)

DMRL: Data- and Model-aware Reward Learning for Data Extraction
by: Wang, Zhiqiang, et al.
Published: (2025)

MRMMIA: Membership Inference Attacks on Memory in Chat Agents
by: Chen, Kai, et al.
Published: (2026)

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
by: Chen, Zhaorun, et al.
Published: (2024)

Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
by: Zhang, Boyang, et al.
Published: (2024)

Cluster Analysis and Concept Drift Detection in Malware
by: Mishra, Aniket, et al.
Published: (2025)

Thwarting Cybersecurity Attacks with Explainable Concept Drift
by: Shaer, Ibrahim, et al.
Published: (2024)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
by: Srivastava, Saksham Sahai, et al.
Published: (2025)

DiPT: Enhancing LLM reasoning through diversified perspective-taking
by: Just, Hoang Anh, et al.
Published: (2024)

Federated Learning Clients Clustering with Adaptation to Data Drifts
by: Li, Minghao, et al.
Published: (2024)

Privacy Drift: Evolving Privacy Concerns in Incremental Learning
by: Ahamed, Sayyed Farid, et al.
Published: (2024)

Understanding Concept Drift with Deprecated Permissions in Android Malware Detection
by: Sabbah, Ahmed, et al.
Published: (2025)

Concept Drift Detection using Ensemble of Integrally Private Models
by: Varshney, Ayush K., et al.
Published: (2024)

What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs
by: Li, Xingyu, et al.
Published: (2025)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
by: Debenedetti, Edoardo, et al.
Published: (2024)

CTFusion: A CTF-based Benchmark for LLM Agent Evaluation
by: Lee, Dongjun, et al.
Published: (2026)

Design Patterns for Securing LLM Agents against Prompt Injections
by: Beurer-Kellner, Luca, et al.
Published: (2025)

Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback
by: Sriram, Vidyut, et al.
Published: (2026)

DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift
by: McFadden, Shae, et al.
Published: (2025)

LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysis
by: Haque, Md Ahsanul, et al.
Published: (2025)

Binary Anomaly Detection in Streaming IoT Traffic under Concept Drift
by: Carnier, Rodrigo Matos, et al.
Published: (2025)

Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
by: He, Pengfei, et al.
Published: (2026)

FARM: Few-shot Adaptive Malware Family Classification under Concept Drift
by: Guldemir, Numan Halit, et al.
Published: (2026)

MADCAT: Combating Malware Detection Under Concept Drift with Test-Time Adaptation
by: Roh, Eunjin, et al.
Published: (2025)

ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection
by: Alam, Md Tanvirul, et al.
Published: (2025)

Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams
by: Gower-Winter, Brandon, et al.
Published: (2024)

Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices
by: Xia, Xiaoyu, et al.
Published: (2024)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
by: Hossain, S M Asif, et al.
Published: (2025)

Detecting Concept Drift in Evolving Malware Families Using Rule-Based Classifier Representations
by: Kalný, Tomáš, et al.
Published: (2026)

McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware
by: Kamol, Md Mahmuduzzaman, et al.
Published: (2026)

Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
by: Jiralerspong, Thomas, et al.
Published: (2026)

Automated Membership Inference Attacks: Discovering MIA Signal Computations using LLM Agents
by: Tran, Toan, et al.
Published: (2026)

SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks
by: Lee, Hwiwon, et al.
Published: (2025)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
by: Zhan, Qiusi, et al.
Published: (2025)

Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols
by: Zavrak, Sultan
Published: (2026)

Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting
by: Ma, Hua, et al.
Published: (2025)

TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents
by: Gong, Chen, et al.
Published: (2024)

Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
by: Dabas, Mahavir, et al.
Published: (2025)

SEED: Semi-supervised Continual MalwarE Detection for Tackling ConcEpt Drift on a BuDget
by: Amalapuram, Suresh Kumar, et al.
Published: (2026)

Policy-Invisible Violations in LLM-Based Agents
by: Wu, Jie, et al.
Published: (2026)