International

Hong Kong police can ask for phone or computer passwords from people they think may have broken the National Security Law (NSL). Those who say no might spend a year in jail and pay a fine of up to HK$100,000 ($12,700; £9,600). People who give “false or misleading information” could go …

The Reserve Bank of India (RBI) has asked banks for feedback on using facial recognition or other AI systems at ATMs, branch counters, and banking places, especially in areas known for fraud. A new digital shield for banking security If put into use, the system would make banking safer. Facial …

Athanasios Rantos, Advocate General of the CJEU, said that banks should quickly refund account holders for unauthorized transactions, regardless of the account holders’ fault. The opinion was issued in response to a request for a preliminary ruling submitted by the District Court in Koszalin, Poland, in a dispute between the …

OpenAI launched Codex Security on Friday, an AI security agent that identifies and suggests fixes for vulnerabilities. The feature is in research preview for ChatGPT Pro, Enterprise, Business, and Edu customers through the Codex web, available free for the next month. “It builds deep context about your project to identify complex …

President Donald Trump ordered all federal agencies to stop using Anthropic on Friday, announcing it on Truth Social shortly before the Pentagon’s deadline for the AI startup to remove military usage restrictions on its Claude AI model. Trump wrote his social truth, “THE UNITED STATES OF AMERICA WILL NEVER ALLOW …

Organizations are reminded that three Windows versions released in 2016 are about to lose support. After the last monthly security update, they won’t receive security patches, bug fixes, non-security updates, support, or updated documentation anymore. End Support for Legacy Windows Versions: For defenders, the key issue is the accumulation of …

ESET researchers discover PromptSpy, the first Android malware using generative AI for persistence. This is the first instance of such AI being used in this way. The attackers use prompts directed at Google’s Gemini to manipulate the UI, leading to the name PromptSpy. The malware can collect lockscreen data, prevent …

Texas sued networking giant TP-Link Systems, accusing the company of deceptively marketing its routers as secure while allowing Chinese state-backed hackers to exploit firmware vulnerabilities and access users’ devices. The lawsuit follows an investigation launched in October and claims that TP-Link misled buyers by labeling its products “Made in Vietnam” …

Guardian is an enterprise-level AI penetration testing tool by Zakir Kun on GitHub. It combines OpenAI GPT-4, Anthropic Claude, Google Gemini, and OpenRouter in a single multi-agent system for smart security assessments and thorough evidence collection. It employs four active agents: Planner, Tool Selector, Analyst, and Reporter. They collaborate on …

OpenAI along with crypto firm Paradigm have launched EVMbench, a benchmark to assess AI agents’ skills in identifying, fixing, and exploiting serious vulnerabilities in smart contracts. EVMbench includes 120 curated vulnerabilities from 40 security audits, primarily from open code audit competitions on platforms like Code4rena. Three Evaluation Modes: EVMbench tests …