Copertina

CoT-Guard: Small Models for Strong Monitoring

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Diwan, Nirav, Wang, Han, Kapusuzoglu, Berkcan, Moradi, Ramin, Chakraborty, Supriyo, Iyengar, Giri, Sahu, Sambit, Zhang, Huan, Wang, Gang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Beyond BeautifulSoup: Benchmarking LLM-Powered Web Scraping for Everyday Users
di: Bhardwaj, Arth, et al.
Pubblicazione: (2026)

SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation
di: Kapusuzoglu, Berkcan, et al.
Pubblicazione: (2025)

Critique-Guided Distillation for Robust Reasoning via Refinement
di: Kapusuzoglu, Berkcan, et al.
Pubblicazione: (2025)

Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
di: Zhao, Bo, et al.
Pubblicazione: (2025)

Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
di: Jiralerspong, Thomas, et al.
Pubblicazione: (2026)

Visual CoT Makes VLMs Smarter but More Fragile
di: Xu, Chunxue, et al.
Pubblicazione: (2025)

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

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

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
di: Wahed, Muntasir, et al.
Pubblicazione: (2025)

CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents
di: Li, Haoyang, et al.
Pubblicazione: (2025)

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
di: Wu, Zhengxian, et al.
Pubblicazione: (2025)

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

CyberLLM-FINDS 2025: Instruction-Tuned Fine-tuning of Domain-Specific LLMs with Retrieval-Augmented Generation and Graph Integration for MITRE Evaluation
di: Iyer, Vasanth, et al.
Pubblicazione: (2026)

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

KinGuard: Hierarchical Kinship-Aware Fingerprinting to Defend Against Large Language Model Stealing
di: Xu, Zhenhua, et al.
Pubblicazione: (2026)

HighGuard: Cross-Chain Business Logic Monitoring of Smart Contracts
di: Eshghie, Mojtaba, et al.
Pubblicazione: (2023)

RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM Routing
di: Zhang, Wenhui, et al.
Pubblicazione: (2026)

Guarding Multiple Secrets: Enhanced Summary Statistic Privacy for Data Sharing
di: Wang, Shuaiqi, et al.
Pubblicazione: (2024)

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

Botnet Detection on CTU-13 Using Lightweight Machine Learning Models
di: Gurappa, Subhash, et al.
Pubblicazione: (2026)

Evaluate and Guard the Wisdom of Crowds: Zero Knowledge Proofs for Crowdsourcing Truth Inference
di: Liu, Xuanming, et al.
Pubblicazione: (2023)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
di: Zhao, Yunhan, et al.
Pubblicazione: (2026)

LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization
di: Yang, Guang, et al.
Pubblicazione: (2026)

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

Understanding Mobile App Reviews to Guide Misuse Audits
di: Garg, Vaibhav, et al.
Pubblicazione: (2023)

X-Guard: Multilingual Guard Agent for Content Moderation
di: Upadhayay, Bibek, et al.
Pubblicazione: (2025)

TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
di: Guo, Zhen, et al.
Pubblicazione: (2026)

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

PhishGuard: A Multi-Layered Ensemble Model for Optimal Phishing Website Detection
di: Ovi, Md Sultanul Islam, et al.
Pubblicazione: (2024)

MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning
di: Wang, Zhiqiang, et al.
Pubblicazione: (2025)

Using Retriever Augmented Large Language Models for Attack Graph Generation
di: Prapty, Renascence Tarafder, et al.
Pubblicazione: (2024)

Revisiting Concept Drift in Windows Malware Detection: Adaptation to Real Drifted Malware with Minimal Samples
di: Li, Adrian Shuai, et al.
Pubblicazione: (2024)

The dark deep side of DeepSeek: Fine-tuning attacks against the safety alignment of CoT-enabled models
di: Xu, Zhiyuan, et al.
Pubblicazione: (2025)

DeFiGuard: A Price Manipulation Detection Service in DeFi using Graph Neural Networks
di: Wang, Dabao, et al.
Pubblicazione: (2024)

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

Bypassing Prompt Guards in Production with Controlled-Release Prompting
di: Fairoze, Jaiden, et al.
Pubblicazione: (2025)

AIRGuard: Guarding Agent Actions with Runtime Authority Control
di: Qin, Suliu, et al.
Pubblicazione: (2026)

On Calibration of LLM-based Guard Models for Reliable Content Moderation
di: Liu, Hongfu, et al.
Pubblicazione: (2024)

ClawGuard: Out-of-Band Detection of LLM Agent Workflow Hijacking via EM Side Channel
di: Gan, Leo Linqian, et al.
Pubblicazione: (2026)

LeakGuard: Detecting Memory Leaks Accurately and Scalably
di: Liang, Hongliang, et al.
Pubblicazione: (2025)