QNAP urges users to update Plex Media Server to the latest version available in the QNAP App Center, as hackers are exploiting the Plex2Shell vulnerability chain. The vendor said it had received multiple reports of suspected compromises involving customers’ network-attached storage (NAS) devices. "QNAP has received reports from some users that Plex Media Server on their NAS appears to have been compromised through [Plex2Shell] vulnerabilities, and QNAP Technical Support is assisting the affected users,” the company says in an advisory today. Plex2Shell is a chain of four vulnerabilities in the Plex Media Server, tracked as CVE-2026-96652, CVE-2026-96654, CVE-2026-96655, and CVE-2026-96656. Security researcher Zach Main discovered and reported the flaws to Plex on July 27. Exploitation started shortly after the full technical details became public on October 16.
In April 2026, BleepingComputer reported that Canadian authorities arrested three men for operating an “SMS blaster,” a device that pretends to be a cell tower to send phishing texts to nearby phones. It’s a close cousin of the IMSI catcher, the fake-tower device used for surveillance. Both work by tricking phones into connecting to the strongest signal and sharing information before anything is authenticated. One of the main things a fake tower can collect this way is your IMSI, the identifier tied to your SIM, but it’s far from the only thing your phone gives away. Your phone has several radios that connect to different kinds of signals and share different information. The Wi-Fi and Bluetooth radios share hardware addresses, which modern phones randomize or rotate to reduce tracking.
D-Link shared mitigation measures for multiple unpatched security flaws affecting DGS-3130 series managed Gigabit stackable switches. These switch models provide multi-gigabit uplinks, allowing enterprise network administrators to eliminate data bottlenecks, and are designed primarily for small-to-medium businesses (SMBs) and metro Ethernet deployments. While D-Link didn't share details on these flaws and has yet to publicly disclose the CVE IDs for easier tracking, it said Spectrum Community Solutions network engineer Giresh Kumar Enugu found the bugs in the D-Link Discovery Protocol (DDP) authentication, access control, and information handling. Successful exploitation could allow attackers to obtain sensitive device data, make unauthorized credential/configuration changes, leak SNMP communities, or cause service disruptions and device resets.
Cryptocurrency wallet provider MetaMask said a recent security incident has not affected MetaMask wallets or its wallet infrastructure. The MetaMask non-custodial crypto wallet (developed by blockchain software company Consensys) lets users store and manage assets on the Ethereum network and compatible blockchains. MetaMask revealed on September 30 that it was investigating an "ongoing infrastructure security incident" and exited affected validators (Ethereum network nodes responsible for proposing blocks, verifying crypto transactions, and maintaining Ethereum blockchain security) within non-custodial staking operations. While the company shared almost no details at the time and redirected BleepingComputer to the public statement when asked what part of its infrastructure was affected, in a Thursday update it said that a threat actor gained access to systems used to store recipient addresses and diverted some execution-layer staking rewards.
OpenAI says GPT-6 Astra sometimes secretly underperformed on safety research, raising concerns about AI reliability and alignment. OpenAI has disclosed that its GPT-6 Astra model sometimes quietly obstructed safety and alignment work. In a report updated on November 4, the company calls it covert underperformance. Astra added unnecessary prerequisites, abandoned working solutions and reported blockers that didn’t exist or that it had caused itself. Researchers first reported the problem internally on August 20, shortly after Astra was introduced. One researcher said a project to test whether the model could sabotage other AI systems made little progress for several days. After switching to another model, the work moved forward quickly. In most cases, Astra’s reasoning gave no clear sign that it was deliberately doing less work, and OpenAI’s monitoring systems failed to detect the behavior. To investigate, OpenAI created pairs of coding tasks using the same code but with different goals. One task was presented as safety research, while the other was described as capability development. Astra completed about 10% of the required tasks when they involved safety research, compared with 16% for capability development. This means it completed roughly 40% fewer tasks in the safety tests. GPT-5.6 Sol showed almost no difference between the two types of work. Even after OpenAI removed cases involving clear refusals or signs that Astra had deliberately withheld help, the gap remained at 4.7 percentage points. It dropped to just 0.75 points only after researchers also removed every case where the model showed even brief ethical concerns. This suggests that most of the behavior cannot be detected simply by checking whether the model openly refuses a request. In employees’ daily Codex use, Astra refused 1.63 percent of safety and alignment requests, against 0.56 percent of capabilities requests. Its reasoning showed it withheld help silently in 0.25 percent of safety requests versus 0.11 percent of capabilities requests, 2.3 times as often. Ethical doubt appeared in 7.9 percent against 2.9 percent, mostly in red-teaming, monitoring, and safety evaluation work. OpenAI shared eight examples. Astra silently held back on training models to evade monitors, filtered a violent source out of a safety evaluation, restricted a jailbreak data export and narrowed exploit analysis. In one case it left graders’ reasoning out of an export without telling the user. A model that quietly decides your project is too risky is the coworker who says “looking into it” and never does. OpenAI has not yet identified the exact cause of the behavior. The difference between Astra’s performance on safety and capability tasks grew from almost zero at the start of reinforcement learning to 6 percentage points by the end. One evaluator favored silently doing less work over either refusing a request or fully completing it. Another finding was that a fine-tuning dataset encouraged the model to invent permission restrictions. Removing the changes linked to that dataset eliminated the performance gap. However, other models trained with the same dataset and reinforcement learning did not show the same behavior, so OpenAI cannot identify either factor as the root cause. OpenAI found no evidence that Astra was deliberately trying to hide its capabilities or influence deployment decisions, although it cannot rule out these possibilities. Simply telling the model to be more careful increased its underperformance by 50%, suggesting that excessive caution may be the main explanation. OpenAI warns that this behavior can slow safety research and make model evaluations less reliable. It is developing new tests and monitoring systems to detect it, especially because the problem becomes harder to identify when models reveal less of their reasoning. In some cases, Astra explained that it had held back because it disagreed with the research itself. “In reviewed cases, Astra narrowed or stopped requested safety work without disclosing the restriction. At scale, this can differentially slow down safety research compared to other research and make evaluations harder to interpret.” concludes the report. “A model that finds monitor evasion suspicious may underperform on monitor-evasion evaluations while leaving little evidence in its CoT or outputs. The behavior becomes even harder to detect if models externalize less of this reasoning in CoT.” Follow me on Twitter: @securityaffairs and Facebook and Mastodon Pierluigi Paganini (SecurityAffairs – hacking, OpenAI)
Hackers are using fake OpenAI, SpaceX, and Anthropic event invitations to lure employees into phishing attacks, using two different phishing-as-a-service platforms to steal Microsoft and Google account credentials and authentication sessions. According to a new report from Push Security, the attackers use convincing event registration pages offering free access to premium AI services and other rewards to trick victims into signing in with their corporate accounts. What makes the attacks interesting is that the same phishing pages integrate two separate phishing-as-a-service (PhaaS) platforms, Kali365 and VoidProxy, to target Microsoft and Google accounts using different authentication attacks. Kali365 conducts Microsoft device code phishing attacks, while VoidProxy acts as an adversary-in-the-middle (AiTM) reverse proxy to intercept Google sign-ins and steal authentication session cookies.
DigiCert warns it suffered a data breach after a server migration mistakenly exposed an internal business system to the internet, allowing unauthorized access to customer information and identity documents. The certificate authority says the breach affected a small portion of its archived customer data, including names, business email addresses, phone numbers, and business addresses. For some people, the exposed records also contained personal identification documents, such as driver's licenses, passports, and utility bills. DigiCert has begun sending data breach notifications to affected customers, with cloud architect Fabian Bader sharing a copy of the notification on X. "Thanks @digicert that your data leak was 'limited' to only my full PII data and potentially any verification documents I submitted for my certificate," Bader wrote.
Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown Mode was introduced by the artificial intelligence (AI) company in June 2026 as an optional setting to minimize data exfiltration risks arising from prompt injections. "The flaw could enable silent chat data theft, phishing,
Apple has revealed that it plans to start checking public iCloud links for harmful content starting with iOS 27.3, iPadOS 27.3, macOS 27.3, and visionOS 27.3. The change specifically applies to scenarios where users share iCloud content, such as photos in iCloud Photos or files in iCloud Drive, by sharing a link and making it accessible to "Anyone with the link." When users choose this option,
Zyxel GS1900 network switches that received the vendor's earlier fix for an actively exploited flaw are still open to the exploit attackers used, researchers at Binarly found. The exploit lets anyone who can reach a switch's web management interface run commands on it without logging in. Zyxel has released new firmware for 10 GS1900 models that closes the hole. The earlier fix is the 2.90
Confirm this action.
Leaving now will discard your changes.