Copertina

Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhou, Shide, Wang, Kailong, Shi, Ling, Wang, Haoyu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
di: Li, Yuxi, et al.
Pubblicazione: (2024)

When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion
di: Li, Jiaqing, et al.
Pubblicazione: (2026)

MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
di: Deng, Gelei, et al.
Pubblicazione: (2023)

Directed Greybox Fuzzing via Large Language Model
di: Xu, Hanxiang, et al.
Pubblicazione: (2025)

Hunting the Ghost: Towards Automatic Mining of IoT Hidden Services
di: Dong, Shuaike, et al.
Pubblicazione: (2025)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
di: Xu, Zihao, et al.
Pubblicazione: (2024)

MalModel: Hiding Malicious Payload in Mobile Deep Learning Models with Black-box Backdoor Attack
di: Hua, Jiayi, et al.
Pubblicazione: (2024)

Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures
di: Wang, Suqing, et al.
Pubblicazione: (2025)

Large Language Models for Cyber Security: A Systematic Literature Review
di: Xu, Hanxiang, et al.
Pubblicazione: (2024)

MATRIX: Multi-Layer Code Watermarking via Dual-Channel Constrained Parity-Check Encoding
di: Nie, Yuqing, et al.
Pubblicazione: (2026)

RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement
di: Wang, Ziye, et al.
Pubblicazione: (2026)

Digger: Detecting Copyright Content Mis-usage in Large Language Model Training
di: Li, Haodong, et al.
Pubblicazione: (2024)

MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis
di: Wang, Shenao, et al.
Pubblicazione: (2024)

Digital Forensics in the Age of Large Language Models
di: Yin, Zhipeng, et al.
Pubblicazione: (2025)

No More Hidden Pitfalls? Exposing Smart Contract Bad Practices with LLM-Powered Hybrid Analysis
di: Li, Xiaoqi, et al.
Pubblicazione: (2025)

SoK: Understanding Vulnerabilities in the Large Language Model Supply Chain
di: Wang, Shenao, et al.
Pubblicazione: (2025)

Evaluating and Enhancing the Vulnerability Reasoning Capabilities of Large Language Models
di: Lu, Li, et al.
Pubblicazione: (2026)

Towards Robust Detection of Open Source Software Supply Chain Poisoning Attacks in Industry Environments
di: Zheng, Xinyi, et al.
Pubblicazione: (2024)

WALLETRADAR: Towards Automating the Detection of Vulnerabilities in Browser-based Cryptocurrency Wallets
di: Xia, Pengcheng, et al.
Pubblicazione: (2024)

GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models
di: Xu, Zuyao, et al.
Pubblicazione: (2026)

Decoding Secret Memorization in Code LLMs Through Token-Level Characterization
di: Nie, Yuqing, et al.
Pubblicazione: (2024)

Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models
di: Yang, Yijun, et al.
Pubblicazione: (2025)

Beyond the Scope: Security Testing of Permission Management in Team Workspace
di: Wan, Liuhuo, et al.
Pubblicazione: (2025)

Secure Information Embedding in Forensic 3D Fingerprinting
di: Wang, Canran, et al.
Pubblicazione: (2024)

ForensicsData: A Digital Forensics Dataset for Large Language Models
di: Chakir, Youssef, et al.
Pubblicazione: (2025)

Time will Tell: Large-scale De-anonymization of Hidden I2P Services via Live Behavior Alignment (Extended Version)
di: Wang, Hongze, et al.
Pubblicazione: (2025)

Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks
di: Collu, Matteo Gioele, et al.
Pubblicazione: (2025)

Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation
di: Wang, Haoyu, et al.
Pubblicazione: (2024)

Exposing Go's Hidden Bugs: A Novel Concolic Framework
di: Gorna, Karolina, et al.
Pubblicazione: (2025)

Measuring and Explaining the Effects of Android App Transformations in Online Malware Detection
di: Meng, Guozhu, et al.
Pubblicazione: (2025)

Exposing Hidden Backdoors in NFT Smart Contracts: A Static Security Analysis of Rug Pull Patterns
di: Pathade, Chetan, et al.
Pubblicazione: (2025)

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
di: Zhao, Jian, et al.
Pubblicazione: (2024)

Large Language Models as Carriers of Hidden Messages
di: Hoscilowicz, Jakub, et al.
Pubblicazione: (2024)

Optimizing IoT Intrusion Detection with Tabular Foundation Models for Smart City Forensics
di: Al-Dahmani, Asma, et al.
Pubblicazione: (2026)

Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency
di: Wickramasekara, Akila, et al.
Pubblicazione: (2024)

Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics
di: Jia, Shan, et al.
Pubblicazione: (2024)

LLM-driven Provenance Forensics for Threat Investigation and Detection
di: Mukherjee, Kunal, et al.
Pubblicazione: (2025)

Yama: Precise Opcode-based Data Flow Analysis for Detecting PHP Applications Vulnerabilities
di: Jiazhen, Zhao, et al.
Pubblicazione: (2024)

CryptoCatch: Cryptomining Hidden Nowhere
di: Shi, Ruisheng, et al.
Pubblicazione: (2026)

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
di: Rayhan, Naheed, et al.
Pubblicazione: (2026)