Cover Image

Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chang, Wenhan, Zhu, Tianqing, Xiong, Ping, Guan, Faqian, Zhou, Wanlei
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation
by: Chang, Wenhan, et al.
Published: (2024)

Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
by: Guan, Faqian, et al.
Published: (2024)

Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives
by: Chang, Wenhan, et al.
Published: (2025)

Large Language Models for Link Stealing Attacks Against Graph Neural Networks
by: Guan, Faqian, et al.
Published: (2024)

Evaluating of Machine Unlearning: Robustness Verification Without Prior Modifications
by: Xu, Heng, et al.
Published: (2024)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
by: Zhou, Shuai, et al.
Published: (2024)

Osmosis Distillation: Model Hijacking with the Fewest Samples
by: Shi, Yuchen, et al.
Published: (2026)

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
by: Zhang, Guangsheng, et al.
Published: (2026)

Really Unlearned? Verifying Machine Unlearning via Influential Sample Pairs
by: Xu, Heng, et al.
Published: (2024)

Don't Forget Too Much: Towards Machine Unlearning on Feature Level
by: Xu, Heng, et al.
Published: (2024)

Federated TrustChain: Blockchain-Enhanced LLM Training and Unlearning
by: Zuo, Xuhan, et al.
Published: (2024)

Large Language Model Federated Learning with Blockchain and Unlearning for Cross-Organizational Collaboration
by: Zuo, Xuhan, et al.
Published: (2024)

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
by: Wang, Shang, et al.
Published: (2024)

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
by: Xiang, Zhen, et al.
Published: (2024)

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions
by: Qi, Minfeng, et al.
Published: (2026)

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
by: Yuan, Zenghui, et al.
Published: (2025)

Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
by: Liu, Chi, et al.
Published: (2020)

MARS: A Malignity-Aware Backdoor Defense in Federated Learning
by: Wan, Wei, et al.
Published: (2025)

From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models
by: Liu, Junhao, et al.
Published: (2025)

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
by: Xu, Zhenhao, et al.
Published: (2026)

The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
by: He, Feng, et al.
Published: (2024)

Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
by: Liu, Chi, et al.
Published: (2025)

Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
by: Liu, Chi, et al.
Published: (2023)

Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
by: Qi, Minfeng, et al.
Published: (2025)

Towards Efficient Target-Level Machine Unlearning Based on Essential Graph
by: Xu, Heng, et al.
Published: (2024)

A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks
by: Liu, Hengzhu, et al.
Published: (2024)

Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey
by: Wang, Shang, et al.
Published: (2024)

DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
by: You, Ziyang, et al.
Published: (2026)

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
by: Liu, Zhichao, et al.
Published: (2026)

Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives
by: Wang, Linlin, et al.
Published: (2024)

Forgetting Similar Samples: Can Machine Unlearning Do it Better?
by: Xu, Heng, et al.
Published: (2026)

CSC: Turning the Adversary's Poison against Itself
by: Shi, Yuchen, et al.
Published: (2026)

DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
by: Guo, Zhen, et al.
Published: (2025)

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
by: Wang, Linlin, et al.
Published: (2025)

ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
by: Zhao, Gejian, et al.
Published: (2025)

When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
by: Tian, Huan, et al.
Published: (2023)

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
by: Huang, Zhengxian, et al.
Published: (2026)

QUEEN: Query Unlearning against Model Extraction
by: Chen, Huajie, et al.
Published: (2024)

Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation
by: Xu, Heng, et al.
Published: (2024)

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
by: Zhang, Guangsheng, et al.
Published: (2022)