Imagen de Portada

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Zhen, Shi, Shanghao, Li, Hao, Yazdani, Shamim, Zhang, Ning, Tourani, Reza
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Persistent Backdoor Attacks in Continual Learning
por: Guo, Zhen, et al.
Publicado: (2024)

TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol
por: Nguyen, Khanh Linh, et al.
Publicado: (2026)

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack
por: Li, Hao, et al.
Publicado: (2025)

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring
por: Hua, Peichun, et al.
Publicado: (2025)

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

Prototype-Guided Robust Learning against Backdoor Attacks
por: Guo, Wei, et al.
Publicado: (2025)

PSRT: Accelerating LRM-based Guard Models via Prefilled Safe Reasoning Traces
por: Zhao, Jiawei, et al.
Publicado: (2025)

AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
por: Li, Hao, et al.
Publicado: (2026)

Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability
por: Li, Chenxi, et al.
Publicado: (2024)

ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models
por: Jin, Heng, et al.
Publicado: (2024)

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

BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
por: Chen, Yulin, et al.
Publicado: (2024)

Combinational Backdoor Attack against Customized Text-to-Image Models
por: Jiang, Wenbo, et al.
Publicado: (2024)

BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
por: Jiang, Zhengyuan, et al.
Publicado: (2024)

Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
por: Ni, Zhenyang, et al.
Publicado: (2024)

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
por: Truong, Vu Tuan, et al.
Publicado: (2026)

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

Stealthy Targeted Backdoor Attacks against Image Captioning
por: Fan, Wenshu, et al.
Publicado: (2024)

Firewalls to Secure Dynamic LLM Agentic Networks
por: Abdelnabi, Sahar, et al.
Publicado: (2025)

Transferring Backdoors between Large Language Models by Knowledge Distillation
por: Cheng, Pengzhou, et al.
Publicado: (2024)

Low Rank Adaptation for Adversarial Perturbation
por: Liu, Han, et al.
Publicado: (2026)

SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
por: Zhang, Hao, et al.
Publicado: (2025)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
por: Guo, Ji, et al.
Publicado: (2024)

ExplainableGuard: Interpretable Adversarial Defense for Large Language Models Using Chain-of-Thought Reasoning
por: Guan, Shaowei, et al.
Publicado: (2025)

Cross-Modal Backdoors in Multimodal Large Language Models
por: Wang, Runhe, et al.
Publicado: (2026)

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
por: Yuan, Zenghui, et al.
Publicado: (2025)

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
por: Fu, Hang, et al.
Publicado: (2026)

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

PoseGuard: Pose-Guided Generation with Safety Guardrails
por: Wang, Kongxin, et al.
Publicado: (2025)

ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning
por: Shui, Yuhan, et al.
Publicado: (2026)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
por: Zhang, Xu, et al.
Publicado: (2025)

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

BadDLM: Backdooring Diffusion Language Models with Diverse Targets
por: Zhai, Shengfang, et al.
Publicado: (2026)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
por: Chen, Yulin, et al.
Publicado: (2026)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
por: Lai, Songning, et al.
Publicado: (2024)

Concept-Guided Backdoor Attack on Vision Language Models
por: Shen, Haoyu, et al.
Publicado: (2025)

Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
por: Hossen, Md Imran, et al.
Publicado: (2024)

Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review
por: Cheng, Pengzhou, et al.
Publicado: (2023)

GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio
por: Zhu, Zhenhao, et al.
Publicado: (2026)