STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Seong-Gyu, Park, Sohee, Lee, Jisu, Na, Hyunsik, Choi, Daeseon
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security
by: Kim, Hajun, et al.
Published: (2025)

Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores
by: Na, Hyunsik, et al.
Published: (2025)

An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
by: Yang, Hongjang, et al.
Published: (2026)

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs
by: Yeo, Andrew, et al.
Published: (2025)

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
by: Lee, Hyomin, et al.
Published: (2026)

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

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

ReGraM: Region-First Knowledge Graph Reasoning for Medical Question Answering
by: Lee, Chaerin, et al.
Published: (2026)

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors
by: Peng, Yuefeng, et al.
Published: (2024)

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

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

Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
by: Tong, Yao, et al.
Published: (2024)

Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation
by: Na, CheolWon, et al.
Published: (2025)

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

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
by: Tong, Terry, et al.
Published: (2025)

Overthinking Loops in Agents: A Structural Risk via MCP Tools
by: Lee, Yohan, et al.
Published: (2026)

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
by: Simoni, Marco, et al.
Published: (2025)

PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration
by: Zhan, Junfei, et al.
Published: (2025)

Confidential Prompting: Privacy-preserving LLM Inference on Cloud
by: Li, Caihua, et al.
Published: (2024)

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

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
by: Zeng, Rui, et al.
Published: (2024)

DUP: Detection-guided Unlearning for Backdoor Purification in Language Models
by: Hu, Man, et al.
Published: (2025)

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

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
by: Li, Haoran, et al.
Published: (2024)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
by: Yang, Wenkai, et al.
Published: (2024)

Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models
by: Panpatil, Siddhant, et al.
Published: (2025)

Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
by: Fortier, Alexandrine, et al.
Published: (2025)

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

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
by: Wang, Jiongxiao, et al.
Published: (2024)

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

MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation
by: Ding, Yidong, et al.
Published: (2025)

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

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
by: Jiang, Peihai, et al.
Published: (2025)

SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
by: He, Xuanli, et al.
Published: (2024)

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

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

Multi-use LLM Watermarking and the False Detection Problem
by: Fu, Zihao, et al.
Published: (2025)

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

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
by: Zhang, Yuyou, et al.
Published: (2025)

Encryption-Friendly LLM Architecture
by: Rho, Donghwan, et al.
Published: (2024)