Copertina

aCAPTCHA: Verifying That an Entity Is a Capable Agent via Asymmetric Hardness

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Zuyao, Li, Xiang, Wu, Fubin, Qiu, Yuqi, Sun, Lu, Miao, FaSheng
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

XMap: Fast Internet-wide IPv4 and IPv6 Network Scanner
di: Li, Xiang, et al.
Pubblicazione: (2026)

IllusionCAPTCHA: A CAPTCHA based on Visual Illusion
di: Ding, Ziqi, et al.
Pubblicazione: (2025)

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

Replacing CAPTCHA with XNO micropayments
di: Tiruvayipati, Sujanavan
Pubblicazione: (2024)

Oedipus: LLM-enchanced Reasoning CAPTCHA Solver
di: Deng, Gelei, et al.
Pubblicazione: (2024)

Perceptual Gaps: ASCII Art and Overlapping Audio as CAPTCHA
di: Chong, Choon-Hou Rafael
Pubblicazione: (2026)

ThermoCAPTCHA: Privacy-Preserving Human Verification with Farm-Resistant Traceable Tokens
di: Paul, Shovon, et al.
Pubblicazione: (2026)

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers
di: Wang, Junyu, et al.
Pubblicazione: (2025)

ACE-GF: A Generative Framework for Atomic Cryptographic Entities
di: Wang, Jian Sheng
Pubblicazione: (2025)

Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation
di: Kharlamova, Arina, et al.
Pubblicazione: (2025)

D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack
di: Nguyen-Le, Hong-Hanh, et al.
Pubblicazione: (2024)

A Hybrid CAPTCHA Combining Generative AI with Keystroke Dynamics for Enhanced Bot Detection
di: Nia, Ayda Aghaei
Pubblicazione: (2025)

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
di: Chen, Zhaorun, et al.
Pubblicazione: (2025)

The Variant of Designated Verifier Signature Scheme with Message Recovery
di: Huang, Hong-Sheng, et al.
Pubblicazione: (2024)

Really Unlearned? Verifying Machine Unlearning via Influential Sample Pairs
di: Xu, Heng, et al.
Pubblicazione: (2024)

Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection
di: Zhou, Yuqi, et al.
Pubblicazione: (2024)

Infrastructure for Valuable, Tradable, and Verifiable Agent Memory
di: Li, Mengyuan, et al.
Pubblicazione: (2026)

Malicious Agent Detection for Robust Multi-Agent Collaborative Perception
di: Zhao, Yangheng, et al.
Pubblicazione: (2023)

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
di: Hu, Haitao, et al.
Pubblicazione: (2025)

VDDP: Verifiable Distributed Differential Privacy under the Client-Server-Verifier Setup
di: Sun, Haochen, et al.
Pubblicazione: (2025)

Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation
di: Du, Xia, et al.
Pubblicazione: (2025)

EnSolver: Uncertainty-Aware Ensemble CAPTCHA Solvers with Theoretical Guarantees
di: Hoang, Duc C., et al.
Pubblicazione: (2023)

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
di: Lin, Junda, et al.
Pubblicazione: (2026)

PhishSigma++: Malicious Email Detection with Typed Entity Relations
di: Shang, Shang, et al.
Pubblicazione: (2026)

Differentially Private Distance Query with Asymmetric Noise
di: Sheng, Weihong, et al.
Pubblicazione: (2025)

Client-Verifiable and Efficient Federated Unlearning in Low-Altitude Wireless Networks
di: Xu, Yuhua, et al.
Pubblicazione: (2026)

From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
di: Ullah, Saad, et al.
Pubblicazione: (2025)

The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents
di: Sah, Tanmay, et al.
Pubblicazione: (2026)

ObliInjection: Order-Oblivious Prompt Injection Attack to LLM Agents with Multi-source Data
di: Wang, Reachal, et al.
Pubblicazione: (2025)

Time-Delayed Publicly Verifiable Quantum Computation for Classical Verifiers
di: Mohammed, Ameer, et al.
Pubblicazione: (2026)

WATER-GS: Toward Copyright Protection for 3D Gaussian Splatting via Universal Watermarking
di: Tan, Yuqi, et al.
Pubblicazione: (2024)

MalTool: Malicious Tool Attacks on LLM Agents
di: Hu, Yuepeng, et al.
Pubblicazione: (2026)

Maris: A Formally Verifiable Privacy Policy Enforcement Paradigm for Multi-Agent Collaboration Systems
di: Cui, Jian, et al.
Pubblicazione: (2025)

AI Agents with Decentralized Identifiers and Verifiable Credentials
di: Garzon, Sandro Rodriguez, et al.
Pubblicazione: (2025)

Smart Cuts: Enhance Active Learning for Vulnerability Detection by Pruning Hard-to-Learn Data
di: Lan, Xiang, et al.
Pubblicazione: (2025)

VOW: Verifiable and Oblivious Watermark Detection for Large Language Models
di: Luan, Xiaokun, et al.
Pubblicazione: (2026)

CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
di: Chen, Yuxi, et al.
Pubblicazione: (2026)

martFL: Enabling Utility-Driven Data Marketplace with a Robust and Verifiable Federated Learning Architecture
di: Li, Qi, et al.
Pubblicazione: (2023)

Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection
di: Graves, Marcus
Pubblicazione: (2026)

VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Traces
di: Grigor, Artem, et al.
Pubblicazione: (2025)