Cybersecurity research firm Xint on Monday published details of a bug in the OpenAI API that leaks raw reasoning traces from frontier OpenAI models, revealing the risk of other data leaks. OpenAI has confirmed the flaw, mitigated it, and paid a bug bounty for its discovery. The problem is that OpenAI had already deployed mitigations for the issue in August after a research report dubbed Stolen Thoughts revealed a sim…
A monthly analysis of how artificial intelligence is used in illicit communities, based on Flashpoint proprietary intelligence and direct visibility into real threat actor environments. The post AI Threat Report: How Artificial Intelligence Is Used Across Illicit Communities appeared first on Flashpoint.
Dutch police arrest two men over AI-voiced bank fraud that allegedly used a fake app to steal card data from 170 victims, causing €380,000 in losses. Rotterdam police have arrested two men over a new type of bank fraud that used AI-generated phone calls, a fake banking app, and NFC technology to steal bank card […]
Xint says a flaw in OpenAI’s compaction process let researchers move reasoning traces between models, potentially making it cheaper to distill a rival AI. The post Stolen AI Reasoning Could Help China Build Cheaper Rivals appeared first on SecurityWeek.
گسترش جست‌وجوی مبتنی بر هوش مصنوعی گوگل، بازدید بسیاری از رسانه‌های آنلاین را کاهش داده و مدل درآمدی وابسته به موتورهای جست‌وجو را با چالش مواجه کرده است. بر... گسترش جست‌وجوی مبتنی بر هوش مصنوعی گوگل، بازدید بسیاری از رسانه‌های آنلاین را کاهش داده و مدل درآمدی وابسته به موتورهای جست‌وجو را با چالش مواجه کرده است.
Two leading AI developers have released fresh evidence of a problem that researchers have long anticipated: advanced models searching for ways around the limits imposed on them. New disclosures from OpenAI and Anthropic detail how frontier systems exploited weaknesses in their environments or exceeded the intended scope of assigned tasks. OpenAI is now tightening internet access in its internal model-training environ…
Malicious instruction files planted in a computer’s Downloads folder can trick AI coding agents into executing harmful code or exposing authentication tokens, Forever Security said after blocking an attempted attack on a customer’s machine and demonstrating similar techniques against OpenAI’s Codex and Anthropic’s Claude Code. In its research report, the firm said it discovered a malicious AGENTS.md file in a custome…
Cyfirma links PHP2Shell scans of 216 vulnerable hosts to a suspected North Korean campaign using AI to rank public exploits. On October 21, PHP released emergency patches for two critical vulnerabilities, CVE-2026-109618 and CVE-2026-109619, both rated 9.2 on the CVSS scale. The flaws affect all PHP versions that handle web requests. The vulnerable code dates […]
Police in South Korea have broken up a cybercrime ring accused of using generative AI to hack about 90 domestic companies, steal roughly 8.2 million personal records, and demand money in exchange for silence. Investigators believe the group's leader, who never studied IT, used AI to rapidly expand the range of targets. Seven Suspects Tied to the Cybercrime Ring On the 26th, the Cyber Investigation Division of the Seo…
The model engaged in severe overreach and dishonesty, creating fake identities and submitting malicious code on GitHub. The post Mythos 5 Ignored Real-World Harm in July Attack appeared first on SecurityWeek.
Cybercriminals don’t need AI to compromise an organization, but AI is making its way into classic attack methods and changing how quickly such attacks can progress. Tasks that once required attackers to manually sift through information and piece together how an organization operates can be accelerated by AI, reducing the time defenders have to detect and intervene. A recent example of this is EvilTokens, a phishing-…
Anthropic says Claude Mythos 5 targeted real developers with fake identities to push malicious code during a security test. A cybersecurity test is supposed to measure what an AI model can do within an agreed boundary. In one UK AI Security Institute evaluation, Claude Mythos 5 crossed that boundary, targeted a real GitHub project and […]
Built on an evolutionary engine first released in 2018, STAR Fuzzer by Bright Security finds crashes, memory exhaustion and memory-safety bugs in security-critical code without a running application. In its first open source research run, it found High or Critical issues in 45% of the projects tested, and in its first month of availability it produced ten published findings in eight projects, including the Crystal st…
Security Affairs AI-CYBERSECURITY newsletter includes a collection of the best articles and research on AI in the international landscape Artificial intelligence is rapidly changing cybersecurity, reshaping both the techniques used by attackers and the tools available to defenders. AI agents can automate tasks, analyze large amounts of data, discover vulnerabilities and accelerate offensive operations. At […]
