Voice-Enabled AI Agents can Perform Common Scams

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fang, Richard, Bowman, Dylan, Kang, Daniel
Formato:	Preprint
Publicado:	2024
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls
por: Badhe, Sanket
Publicado: (2025)

LLM Agents can Autonomously Exploit One-day Vulnerabilities
por: Fang, Richard, et al.
Publicado: (2024)

LLM Agents can Autonomously Hack Websites
por: Fang, Richard, et al.
Publicado: (2024)

CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments
por: Jaipuria, Nitish, et al.
Publicado: (2025)

Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
por: Zhu, Yuxuan, et al.
Publicado: (2024)

SCRIPTMIND: Crime Script Inference and Cognitive Evaluation for LLM-based Social Engineering Scam Detection System
por: Kim, Heedou, et al.
Publicado: (2026)

ASRJam: Human-Friendly AI Speech Jamming to Prevent Automated Phone Scams
por: Grabovski, Freddie, et al.
Publicado: (2025)

ScamSpot: Fighting Financial Fraud in Instagram Comments
por: Erben, Stefan, et al.
Publicado: (2024)

Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance
por: Chang, Chen-Wei, et al.
Publicado: (2024)

Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
por: Chen, Zhiyang, et al.
Publicado: (2025)

Love, Lies, and Language Models: Investigating AI's Role in Romance-Baiting Scams
por: Gressel, Gilad, et al.
Publicado: (2025)

CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
por: Zhu, Yuxuan, et al.
Publicado: (2025)

ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines
por: Jin, Tengjun, et al.
Publicado: (2025)

Empowering Biomedical Discovery with AI Agents
por: Gao, Shanghua, et al.
Publicado: (2024)

Memory OS of AI Agent
por: Kang, Jiazheng, et al.
Publicado: (2025)

Voices in the Loop: Mapping Participatory AI
por: Mushkani, Rashid
Publicado: (2026)

Back to Basics: Revisiting ASR in the Age of Voice Agents
por: Tay, Geeyang, et al.
Publicado: (2026)

i-LAVA: Insights on Low Latency Voice-2-Voice Architecture for Agents
por: Purwar, Anupam, et al.
Publicado: (2025)

$τ$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
por: Ray, Soham, et al.
Publicado: (2026)

Distinguishing Scams and Fraud with Ensemble Learning
por: Chadalavada, Isha, et al.
Publicado: (2024)

VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series
por: Xu, Pengyu, et al.
Publicado: (2025)

In-Context Learning can Perform Continual Learning Like Humans
por: Kang, Liuwang, et al.
Publicado: (2025)

Cloning a Conversational Voice AI Agent from Call\,Recording Datasets for Telesales
por: Kaewtawee, Krittanon, et al.
Publicado: (2025)

Behavior Trees Enable Structured Programming of Language Model Agents
por: Kelley, Richard
Publicado: (2024)

Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-Agent AI
por: Deck, Luca, et al.
Publicado: (2026)

ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense
por: Lau, Nancy, et al.
Publicado: (2026)

In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making
por: Fok, Raymond, et al.
Publicado: (2023)

Evaluating a Multi-Agent Voice-Enabled Smart Speaker for Care Homes: A Safety-Focused Framework
por: Dehghani, Zeinab, et al.
Publicado: (2026)

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
por: Sun, Jingwei, et al.
Publicado: (2026)

Reasonably reasoning AI agents can avoid game-theoretic failures in zero-shot, provably
por: Kang, Enoch Hyunwook
Publicado: (2026)

Scam Shield: Multi-Model Voting and Fine-Tuned LLMs Against Adversarial Attacks
por: Chang, Chen-Wei, et al.
Publicado: (2025)

Bot Wars Evolved: Orchestrating Competing LLMs in a Counterstrike Against Phone Scams
por: Basta, Nardine, et al.
Publicado: (2025)

STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems
por: Shen, Alfred, et al.
Publicado: (2026)

VoiceAgentBench: Are Voice Assistants ready for agentic tasks?
por: Jain, Dhruv, et al.
Publicado: (2025)

The AI Agent Index
por: Casper, Stephen, et al.
Publicado: (2025)

Where Common Knowledge Cannot Be Formed, Common Belief Can -- Planning with Multi-Agent Belief Using Group Justified Perspectives
por: Hu, Guang, et al.
Publicado: (2024)

An Agent-Based Framework for Automated Higher-Voice Harmony Generation
por: Ganapathy, Nia D'Souza, et al.
Publicado: (2025)

From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
por: Xu, Ke, et al.
Publicado: (2026)

Where LLM Agents Fail and How They can Learn From Failures
por: Zhu, Kunlun, et al.
Publicado: (2025)

The Agent Behavior: Model, Governance and Challenges in the AI Digital Age
por: Zhang, Qiang, et al.
Publicado: (2025)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
ui	"standard"
language	"es"
VUFIND_SESSION	"a5738a277746488b1f7aefb35f6d1152"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790843670.0782 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "a5738a277746488b1f7aefb35f6d1152" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"ui=standard; language=es; VUFIND_SESSION=a5738a277746488b1f7aefb35f6d1152"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.216.147"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"52579"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2410_15650/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2410_15650/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790843670.0613
REQUEST_TIME	1790843670

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler