Copertina

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Domico, Kyle, Ferrand, Jean-Charles Noirot, Sheatsley, Ryan, Pauley, Eric, Hanna, Josiah, McDaniel, Patrick
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Role of Learning in Attacking ML-based Network Intrusion Detection
di: Domico, Kyle, et al.
Pubblicazione: (2026)

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
di: Ferrand, Jean-Charles Noirot, et al.
Pubblicazione: (2025)

Longitudinal Analyses of SAST Tools: A CodeQL Case Study
di: Ferrand, Jean-Charles Noirot, et al.
Pubblicazione: (2026)

Secure IP Address Allocation at Cloud Scale
di: Pauley, Eric, et al.
Pubblicazione: (2022)

Characterizing the Modification Space of Signature IDS Rules
di: Guide, Ryan, et al.
Pubblicazione: (2024)

Efficient Storage Integrity in Adversarial Settings
di: Burke, Quinn, et al.
Pubblicazione: (2025)

LibIHT: A Hardware-Based Approach to Efficient and Evasion-Resistant Dynamic Binary Analysis
di: Zhao, Changyu, et al.
Pubblicazione: (2025)

ParTEETor: A System for Partial Deployments of TEEs within Tor
di: King, Rachel, et al.
Pubblicazione: (2024)

Err on the Side of Texture: Texture Bias on Real Data
di: Hoak, Blaine, et al.
Pubblicazione: (2024)

On Scalable Integrity Checking for Secure Cloud Disks
di: Burke, Quinn, et al.
Pubblicazione: (2024)

Securing Cloud File Systems with Trusted Execution
di: Burke, Quinn, et al.
Pubblicazione: (2023)

ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
di: He, Ningyuan, et al.
Pubblicazione: (2026)

Explainability Guided Adversarial Evasion Attacks on Malware Detectors
di: Aryal, Kshitiz, et al.
Pubblicazione: (2024)

A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems
di: Liu, Zixuan, et al.
Pubblicazione: (2025)

A Public and Reproducible Assessment of the Topics API on Real Data
di: Beugin, Yohan, et al.
Pubblicazione: (2024)

Technical Report: The Need for a (Research) Sandstorm through the Privacy Sandbox
di: Beugin, Yohan, et al.
Pubblicazione: (2025)

Effectiveness of Adversarial Benign and Malware Examples in Evasion and Poisoning Attacks
di: Kozák, Matouš, et al.
Pubblicazione: (2025)

On the Robustness Tradeoff in Fine-Tuning
di: Li, Kunyang, et al.
Pubblicazione: (2025)

Distributional Black-Box Model Inversion Attack with Multi-Agent Reinforcement Learning
di: Bao, Huan, et al.
Pubblicazione: (2024)

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
di: Kang, Mintong, et al.
Pubblicazione: (2023)

Mitigating Evasion Attacks in Fog Computing Resource Provisioning Through Proactive Hardening
di: Salmi, Younes, et al.
Pubblicazione: (2026)

Adversarial Attacks on Reinforcement Learning Agents for Command and Control
di: Dabholkar, Ahaan, et al.
Pubblicazione: (2024)

Black-Box Evasion Attacks on Data-Driven Open RAN Apps: Tailored Design and Experimental Evaluation
di: Gajjar, Pranshav, et al.
Pubblicazione: (2025)

A Semi Black-Box Adversarial Bit-Flip Attack with Limited DNN Model Information
di: Ghavami, Behnam, et al.
Pubblicazione: (2024)

Vulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS
di: Ennaji, Sabrine, et al.
Pubblicazione: (2025)

Intra-Section Code Cave Injection for Adversarial Evasion Attacks on Windows PE Malware File
di: Aryal, Kshitiz, et al.
Pubblicazione: (2024)

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
di: Wang, Zihan, et al.
Pubblicazione: (2026)

ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks
di: Elnawawy, Mohammed, et al.
Pubblicazione: (2026)

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
di: Li, Jiate, et al.
Pubblicazione: (2026)

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
di: Vo, Viet Quoc, et al.
Pubblicazione: (2024)

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
di: Zhong, Xingwei, et al.
Pubblicazione: (2025)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
di: Hong, Hanbin, et al.
Pubblicazione: (2023)

How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World
di: Panebianco, Francesco, et al.
Pubblicazione: (2025)

Targeted Physical Evasion Attacks in the Near-Infrared Domain
di: Zimmer, Pascal, et al.
Pubblicazione: (2025)

Behavior-Aware and Generalizable Defense Against Black-Box Adversarial Attacks for ML-Based IDS
di: Ennaji, Sabrine, et al.
Pubblicazione: (2025)

It's a Feature, Not a Bug: Secure and Auditable State Rollback for Confidential Cloud Applications
di: Burke, Quinn, et al.
Pubblicazione: (2025)

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors
di: Najt, Elle, et al.
Pubblicazione: (2026)

Variational Autoencoder-Based Black-Box Adversarial Attack on Collaborative DNN Inference
di: Yousefi, Shima, et al.
Pubblicazione: (2025)

Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks
di: Bokobza, Roey, et al.
Pubblicazione: (2024)

Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
di: Park, Jeonghwan, et al.
Pubblicazione: (2025)