Cover Image

ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Gejian, Wu, Hanzhou, Zhang, Xinpeng, Vasilakos, Athanasios V.
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Trigger Where It Hurts: Unveiling Hidden Backdoors through Sensitivity with Sensitron
by: Zhao, Gejian, et al.
Published: (2025)

Yet Another Watermark for Large Language Models
by: Bao, Siyuan, et al.
Published: (2025)

Rotation, Scale, and Translation Resilient Black-box Fingerprinting for Intellectual Property Protection of EaaS Models
by: Zhang, Hongjie, et al.
Published: (2025)

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
by: Wei, Jiali, et al.
Published: (2026)

SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
by: Xue, Eric, et al.
Published: (2025)

An Information Asymmetry Game for Trigger-based DNN Model Watermarking
by: Huang, Chaoyue, et al.
Published: (2025)

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
by: Yin, Rui, et al.
Published: (2026)

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
by: Li, Ziqiang, et al.
Published: (2024)

Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
by: Zhao, Xiangyu, et al.
Published: (2024)

R-CoT: A Reasoning-Layer Watermark via Redundant Chain-of-Thought in Large Language Models
by: Zhang, Ziming, et al.
Published: (2026)

Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
by: Li, Xiang, et al.
Published: (2025)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
by: Cao, Yuanpu, et al.
Published: (2023)

Robust and Imperceptible Black-box DNN Watermarking Based on Fourier Perturbation Analysis and Frequency Sensitivity Clustering
by: Liu, Yong, et al.
Published: (2022)

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
by: Wen, Rui, et al.
Published: (2026)

PARASITE: Conditional System Prompt Poisoning to Hijack LLMs
by: Pham, Viet, et al.
Published: (2025)

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
by: Zhang, Yuanhe, et al.
Published: (2025)

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

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
by: Zhao, Shuai, et al.
Published: (2025)

Generative Model Watermarking Suppressing High-Frequency Artifacts
by: Zhang, Li, et al.
Published: (2023)

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

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
by: He, Xuanli, et al.
Published: (2024)

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs
by: Sivapiromrat, Sanhanat, et al.
Published: (2025)

Breaking PEFT Limitations: Leveraging Weak-to-Strong Knowledge Transfer for Backdoor Attacks in LLMs
by: Zhao, Shuai, et al.
Published: (2024)

Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
by: Dai, Yanbo, et al.
Published: (2025)

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
by: Wang, Zihan, et al.
Published: (2025)

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
by: Wang, Zihan, et al.
Published: (2025)

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
by: Cheng, Pengzhou, et al.
Published: (2024)

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges
by: Ding, Ruomeng, et al.
Published: (2026)

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
by: Wu, Zhengxian, et al.
Published: (2025)

BadActs: A Universal Backdoor Defense in the Activation Space
by: Yi, Biao, et al.
Published: (2024)

Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
by: Price, Sara, et al.
Published: (2024)

In-Context Representation Hijacking
by: Yona, Itay, et al.
Published: (2025)

HauntAttack: When Attack Follows Reasoning as a Shadow
by: Ma, Jingyuan, et al.
Published: (2025)

Rethinking Backdoor Detection Evaluation for Language Models
by: Yan, Jun, et al.
Published: (2024)

Hijacking Large Language Models via Adversarial In-Context Learning
by: Zhou, Xiangyu, et al.
Published: (2023)

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
by: Zeng, Yizhe, et al.
Published: (2026)

DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning
by: Wang, Jiayao, et al.
Published: (2026)

Do Reasoning LLMs Refuse What They Infer in Long Contexts?
by: Fu, Yu, et al.
Published: (2026)

Task-Agnostic Detector for Insertion-Based Backdoor Attacks
by: Lyu, Weimin, et al.
Published: (2024)

Under-confidence Backdoors Are Resilient and Stealthy Backdoors
by: Peng, Minlong, et al.
Published: (2022)