Attackers are exploiting a critical-severity privilege escalation vulnerability (CVE-2025-8489) in the King Addons for Elementor plugin for WordPress, which lets them obtain administrative permissions during the registration process. […] Read More
Freedom Mobile, the fourth-largest wireless carrier in Canada, has disclosed a data breach after attackers hacked into its customer account management platform and stole the personal information of an undisclosed number of customers. […] Read More
A maximum-severity security flaw has been disclosed in React Server Components (RSC) that, if successfully exploited, could result in remote code execution. The vulnerability, tracked as CVE-2025-55182, carries a CVSS score of 10.0. It allows “unauthenticated remote code execution by exploiting a flaw in how React decodes payloads sent to React Server Function endpoints,” the […]
A critical security flaw impacting a WordPress plugin known as King Addons for Elementor has come under active exploitation in the wild. The vulnerability, CVE-2025-8489 (CVSS score: 9.8), is a case of privilege escalation that allows unauthenticated attackers to grant themselves administrative privileges by simply specifying the administrator user role during registration. It affects versions Read […]
The China-based cyber-threat group has been quietly using malicious extensions on the Google Chrome and Microsoft Edge marketplaces to spy on millions of users. Read More
Financial software provider Marquis Software Solutions is warning that it suffered a data breach that impacted dozens of banks and credit unions across the US. […] Read More
DragonForce expanded its ransomware operation in 2025 by working with English-speaking hackers known for advanced social engineering and initial access. Acronis explains how the “Scattered Spider” collaboration enables coordinated, multistage intrusions across major environments. […] Read More
TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?cs.AI updates on arXiv.org arXiv:2512.02261v1 Announce Type: new
Abstract: LLM-based trading agents are increasingly deployed in real-world financial markets to perform autonomous analysis and execution. However, their reliability and robustness under adversarial or faulty conditions remain largely unexamined, despite operating in high-risk, irreversible financial environments. We propose TradeTrap, a unified evaluation framework for systematically stress-testing both adaptive and procedural autonomous trading agents. TradeTrap targets four core components of autonomous trading agents: market intelligence, strategy formulation, portfolio and ledger handling, and trade execution, and evaluates their robustness under controlled system-level perturbations. All evaluations are conducted in a closed-loop historical backtesting setting on real US equity market data with identical initial conditions, enabling fair and reproducible comparisons across agents and attacks. Extensive experiments show that small perturbations at a single component can propagate through the agent decision loop and induce extreme concentration, runaway exposure, and large portfolio drawdowns across both agent types, demonstrating that current autonomous trading agents can be systematically misled at the system level. Our code is available at https://github.com/Yanlewen/TradeTrap.
arXiv:2512.02261v1 Announce Type: new
Abstract: LLM-based trading agents are increasingly deployed in real-world financial markets to perform autonomous analysis and execution. However, their reliability and robustness under adversarial or faulty conditions remain largely unexamined, despite operating in high-risk, irreversible financial environments. We propose TradeTrap, a unified evaluation framework for systematically stress-testing both adaptive and procedural autonomous trading agents. TradeTrap targets four core components of autonomous trading agents: market intelligence, strategy formulation, portfolio and ledger handling, and trade execution, and evaluates their robustness under controlled system-level perturbations. All evaluations are conducted in a closed-loop historical backtesting setting on real US equity market data with identical initial conditions, enabling fair and reproducible comparisons across agents and attacks. Extensive experiments show that small perturbations at a single component can propagate through the agent decision loop and induce extreme concentration, runaway exposure, and large portfolio drawdowns across both agent types, demonstrating that current autonomous trading agents can be systematically misled at the system level. Our code is available at https://github.com/Yanlewen/TradeTrap. Read More
Google is expanding support for its Android’s in-call scam protection to multiple banks and financial applications in the United States. […] Read More
In just three months, the massive Aisuru botnet launched more than 1,300 distributed denial-of-service attacks, one of them setting a new record with a peak at 29.7 terabits per second. […] Read More
