Cover Image

Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pallakonda, Bhanu, Hindsbo, Mikkel, Ehsani, Sina, Mishra, Prag
Format:	Preprint
Published:	2026
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

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
by: Chen, Zhuowei, et al.
Published: (2025)

Injecting Bias into Text Classification Models using Backdoor Attacks
by: Yavuz, A. Dilara, et al.
Published: (2024)

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
by: Boisvert, Léo, et al.
Published: (2025)

Camera Control at the Edge with Language Models for Scene Understanding
by: Buynitsky, Alexiy, et al.
Published: (2025)

Prompt Inject Detection with Generative Explanation as an Investigative Tool
by: Pan, Jonathan, et al.
Published: (2025)

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
by: Yu, Haiyang, et al.
Published: (2024)

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
by: An, Shengwei, et al.
Published: (2023)

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
by: Li, Yige, et al.
Published: (2026)

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
by: Guo, Weiyang, et al.
Published: (2026)

Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistency
by: Wang, Bingzheng, et al.
Published: (2026)

Medical Malice: A Dataset for Context-Aware Safety in Healthcare LLMs
by: D'addario, Andrew Maranhão Ventura
Published: (2025)

From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
by: Shen, Guangyu, et al.
Published: (2025)

Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
by: Hu, Man, et al.
Published: (2025)

Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs
by: Cui, Jing, et al.
Published: (2025)

Beyond Immediate Activation: Temporally Decoupled Backdoor Attacks on Time Series Forecasting
by: Liu, Zhixin, et al.
Published: (2026)

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
by: Yan, Shenao, et al.
Published: (2024)

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations
by: Zhou, Yihe, et al.
Published: (2025)

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
by: Zhang, Wuyang, et al.
Published: (2026)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
by: Hubinger, Evan, et al.
Published: (2024)

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
by: Yu, Miao, et al.
Published: (2025)

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
by: Fastowski, Alina, et al.
Published: (2025)

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models
by: Ding, Zikang, et al.
Published: (2026)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, et al.
Published: (2025)

Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing
by: Fan, Kaisheng, et al.
Published: (2026)

Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance
by: Liu, Fazhong, et al.
Published: (2026)

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
by: Wang, Che, et al.
Published: (2026)

Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras
by: Riaño, Roberto, et al.
Published: (2024)

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
by: Wang, Qingyue, et al.
Published: (2025)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
by: Zou, Wei, et al.
Published: (2026)

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
by: Abdelnabi, Sahar, et al.
Published: (2025)

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
by: Ge, Huaizhi, et al.
Published: (2024)

DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
by: Popovic, Dorde, et al.
Published: (2025)

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

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

Backdooring Bias in Large Language Models
by: Das, Anudeep, et al.
Published: (2026)

Lightweight and Fast Backdoor Model Detection
by: Yu, Yinbo, et al.
Published: (2026)

Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?
by: Quantrill, Jason, et al.
Published: (2026)

The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative
by: Tan, Zhen, et al.
Published: (2024)

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
by: Ji, Wence, et al.
Published: (2025)

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
by: Zhao, Shuai, et al.
Published: (2024)