Copertina

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ranganath, Suraj, Ramesh, Atharv
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AuthorMist: Evading AI Text Detectors with Reinforcement Learning
di: David, Isaac, et al.
Pubblicazione: (2025)

Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors
di: Sun, Luze, et al.
Pubblicazione: (2026)

Optimal Zero-Shot Detector for Multi-Armed Attacks
di: Granese, Federica, et al.
Pubblicazione: (2024)

Adversarial Attacks on Transformers-Based Malware Detectors
di: Jakhotiya, Yash, et al.
Pubblicazione: (2022)

RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction
di: Yang, Yingguang, et al.
Pubblicazione: (2025)

Evading Deep Learning-Based Malware Detectors via Obfuscation: A Deep Reinforcement Learning Approach
di: Etter, Brian, et al.
Pubblicazione: (2024)

A General Black-box Adversarial Attack on Graph-based Fake News Detectors
di: Zhu, Peican, et al.
Pubblicazione: (2024)

Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors
di: Choi, Jinhyeok, et al.
Pubblicazione: (2024)

A Novel Perturb-ability Score to Mitigate Evasion Adversarial Attacks on Flow-Based ML-NIDS
di: elShehaby, Mohamed, et al.
Pubblicazione: (2024)

TBDetector:Transformer-Based Detector for Advanced Persistent Threats with Provenance Graph
di: Wang, Nan, et al.
Pubblicazione: (2023)

TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors
di: Zheng, Jingyi, et al.
Pubblicazione: (2025)

Multi-Agent Reinforcement Learning for Assessing False-Data Injection Attacks on Transportation Networks
di: Eghtesad, Taha, et al.
Pubblicazione: (2023)

EGAN: Evolutional GAN for Ransomware Evasion
di: Commey, Daniel, et al.
Pubblicazione: (2024)

Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection
di: Dautartas, Juozas, et al.
Pubblicazione: (2026)

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
di: Domico, Kyle, et al.
Pubblicazione: (2025)

Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
di: Deshmukh, Atharv
Pubblicazione: (2024)

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
di: Li, Yuexin, et al.
Pubblicazione: (2026)

Learning to Watermark LLM-generated Text via Reinforcement Learning
di: Xu, Xiaojun, et al.
Pubblicazione: (2024)

BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
di: Fang, Jing, et al.
Pubblicazione: (2025)

Leveraging Reinforcement Learning in Red Teaming for Advanced Ransomware Attack Simulations
di: Wang, Cheng, et al.
Pubblicazione: (2024)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
di: Xu, Yinglun, et al.
Pubblicazione: (2024)

Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
di: Lee, Sunwoo, et al.
Pubblicazione: (2025)

SubstratumGraphEnv: Reinforcement Learning Environment (RLE) for Modeling System Attack Paths
di: Adewunmi, Bahirah, et al.
Pubblicazione: (2026)

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
di: Ma, Oubo, et al.
Pubblicazione: (2025)

Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
di: Yichao, Wu, et al.
Pubblicazione: (2025)

Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors
di: Staněk, Vojtěch, et al.
Pubblicazione: (2026)

Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines
di: Ahad, Tanzim, et al.
Pubblicazione: (2026)

Training RL Agents for Multi-Objective Network Defense Tasks
di: Molina-Markham, Andres, et al.
Pubblicazione: (2025)

Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
di: Choudhary, Sarthak, et al.
Pubblicazione: (2026)

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
di: Guo, Qiming, et al.
Pubblicazione: (2025)

Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation
di: Liu, Peizhuo
Pubblicazione: (2025)

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
di: Kirci, Onur Alp, et al.
Pubblicazione: (2025)

Mitigating Label Flipping Attacks in Malicious URL Detectors Using Ensemble Trees
di: Nowroozi, Ehsan, et al.
Pubblicazione: (2024)

NetDeTox: Adversarial and Efficient Evasion of Hardware-Security GNNs via RL-LLM Orchestration
di: Wang, Zeng, et al.
Pubblicazione: (2025)

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
di: Terekhov, Mikhail, et al.
Pubblicazione: (2025)

Runtime Detection of Adversarial Attacks in AI Accelerators Using Performance Counters
di: Rahaman, Habibur, et al.
Pubblicazione: (2025)

Attention Masks Help Adversarial Attacks to Bypass Safety Detectors
di: Shi, Yunfan
Pubblicazione: (2024)

PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense
di: Cadet, Xavier, et al.
Pubblicazione: (2025)

VTarbel: Targeted Label Attack with Minimal Knowledge on Detector-enhanced Vertical Federated Learning
di: Tan, Juntao, et al.
Pubblicazione: (2025)

Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources
di: Rajendran, Suraj, et al.
Pubblicazione: (2023)