GLOBEALERT
Sign in

Feed

Open sources, classified and cross-checked. 313+ stories.

AllConflictMilitaryPoliticsBusinessSci & TechCyberDisasterHealthWorld
24h3 days7 days30 daysAll·All regionsNorth AmericaSouth AmericaWestern EuropeEastern EuropeBalticsMiddle EastNorth AfricaSub-Saharan AfricaSouth AsiaEast AsiaOceania
CYBERSep 26OpenAI admits AI agents posted ChatGPT users’ images online in errorThe company also confirmed a New York Times report that its tools had accessed websites of US federal agencies, saying they retrieved only publicly available information. The post OpenAI admits AI agents posted ChatGPT users’ images online in error appeared first on Vanguard News.Vanguard Nigeria
CYBERSep 26OpenAI tools post user images from ChatGPT onlineOpenAI said it found 53 cases in which user-uploaded image links on ChatGPT were shared with third-party websites. The company said it had removed most of these links.DW News [en]
CYBERSep 26OpenAI says its AI agents posted user images online in errorOpenAI acknowledged on Friday that its artificial intelligence tools had posted images from ChatGPT users onto online sites without the company’s knowledge, the latest example of AI agents operating outside their bounds. The company also confirmed a New York Times report that its tools had accessed websites of US federal agencies, saying they retrieved only publicly available information. Links to the 53 uploaded images were not publicly listed and were accidentally posted on image-hosting...South China Morning Post
CYBERSep 26OpenAI says its AI agents posted user images online in errorOpenAI stated that its AI agents mistakenly posted user images online. This indicates a privacy breach concerning user data handled by AI systems.timesofmalta · malta
CYBERSep 26OpenAI’s AI Agents Tried Hacking 4 Websites Without Being PromptedOpenAI’s autonomous AI agents attempted to hack four government, university, and public-data systems while carrying out routine information-gathering tasks, according to researchers and government officials. The agents were not instructed to conduct cyberattacks; when normal retrieval methods failed, they allegedly escalated to vulnerability probing, access-control bypasses, and other intrusive techniques, exposing a critical safety problem […] The post OpenAI’s AI Agents Tried Hacking 4 Websites Without Being Prompted appeared first on Cyber Security News .cybersecuritynews · united states of america
CYBERSep 26Cyber security stocks are pumped up on P(doom)Besieged by growing cyber threats, organisations are hurling money at the problemFinancial Times
CYBERSep 26OpenAI says its AI agents posted users' images online in errorLe Monde [en]
CYBERSep 26OpenAI says its models engaged with US government websites in new model misbehavior disclosure - AP NewsOpenAI says its models engaged with US government websites in new model misbehavior disclosure AP NewsAP News
CYBERSep 26OpenAI acknowledges that its tools accidentally published images of ChatGPT usersOpenAI admitted to the accidental disclosure of 53 user images, hosted on websites, due to an error in its AI tools. The company assures that most have already been removed and is reviewing the activity of its agents to prevent future security incidents.Clarín
CYBERSep 25OpenAI investigating 'dozens' of instances of agents acting improperlyOpenAI said its bots accessed public data from a range of institutions during test exercises.BBC World
CYBERSep 25OpenAI agents posted user images online, disclose dozens of third party incidentsOpenAI disclosed dozens of incidents in which its models behaved in ways it has deemed problematic, including leaking more than 50 images from ChatGPT users online.Why it matters: This is the first publicly known example of the company's agents mishandling user data and the latest example a budding rogue agent problem at OpenAI.The company says it could take months to fully investigate the security incidents.State of play: OpenAI said that some of its agents sent data from its internal training and testing systems to outside websites, including user images, as reported first by Reuters. The coAxios
CYBERSep 25OpenAI agents posted user images online, disclose dozens of third party incidentsOpenAI disclosed dozens of incidents in which its models behaved in ways it has deemed problematic, including leaking more than 50 images from ChatGPT users online. Why it matters : This is the first publicly known example of the company's agents mishandling user data and the latest example a budding rogue agent problem at OpenAI. The company says it could take months to fully investigate the security incidents. State of play : OpenAI said that some of its agents sent data from its internal training and testing systems to outside websites, including user images, as reported first by Reuters . The company identified 53 instances in which images that users put into ChatGPT were then posted to image-hosting sites as links that were not publicly listed. The images came from users whose ChatGPT data was eligible to be used for model training because they had not opted out. OpenAI said it has worked with hosting providers to remove most of the images. It is still trying to remove the rest, meaning some of these images remain public. Zoom out: The images are part of a much broader investigation from the company into AI agents taking actions outside their intended programming, or what's called misaligned behavior. As of mid-September, OpenAI had found roughly two dozen incidents of agents behaving in undesirable ways, according to a person briefed on the matter cited by Reuters. OpenAI says it has already notified dozens of third parties whose websites or services may have been affected and would disclose additional incidents to those impacted: "As we verify cases that meet our disclosure criteria, we are notifying affected organizations and sharing technical findings to support their investigations." Between the lines: This is likely to draw attention to the ChatGPT-maker's security protocols and the challenges it and other AI companies face in controlling their technology. The review began after OpenAI disclosed in July that agents escaped their restricted environment and compromised Hugging Face , an AI startup. OpenAI still calls that the most severe incident of this kind it has identified. The company now says it initially viewed the episode primarily as a cybersecurity breach, but later concluded it was part of a broader pattern of models using misaligned strategies to accomplish difficult tasks. Threat level: OpenAI emphasized that enterprise and business data is excluded from model training by default, meaning it would not have been included in the training data involved in these incidents unless an administrator had opted in. But the broader disclosure comes amid increased concern about enterprise data protection . "It's certainly plausible that an enterprise user could give an agent an instruction, and that agent has access to sensitive information, and that agent takes some sort of action which reveals aspects of that sensitive information," researcher Conrad Stosz at Transluce told Axios. The research said said it uncovered details about OpenAI agents that breached an Australian government website . The bottom line: Security researchers and AI executives expect disclosures about misaligned behavior from companies to continue.axios · united states of america
CYBERSep 25OpenAI says governments among ‘dozens’ of organisations hacked by its agentsFinancial Times
CYBERSep 25EXCLUSIVE: OpenAI works to understand full scope of agent activity as user data leak emerges - ReutersReuters World
CYBERSep 25‘Cyber magazine’ can run out ‘pretty damn quick’ in modern conflict: AdmiralIn the wake of public debates about the health of physical US munitions, a senior Navy official said the “cyber magazine” isn’t infinite either.Breaking Defense
CYBERSep 25A US jury declares Meta responsible in Cambridge Analytica caseA jury in the US found a social network guilty of misleading users about their privacy, linked to the case of a political consultancy. The affected state is seeking millionaire sanctions for massive violations of consumer protection laws.Clarín
CYBERSep 25AI Sandbox Escapes: Why Forensic Readiness Matters More Than ContainmentWhen autonomous AI agents "escape the sandbox," the real story isn't rogue machines — it's the same access-control failures we've seen for decades.Dark Reading
CYBERSep 25What We Missed: Google Gemini Joins the AI Escape PartyIn this video conversation, Dark Reading editors discuss some of the news they didn't get a chance to cover, from Google Gemini models breaking containment to ShinyHunters ratting on TeamPCP hackers.Dark Reading
CYBERSep 25Stopping IT Worker Scams Requires Revamped HR ProcessTraining human-resource managers in the latest tactics and warning signs goes a long way toward blunting the threat, but automated analysis can help even more.Dark Reading
CYBERSep 25Compromised GitHub Actions Came Back Online and Resumed Executing Mini Shai-Hulud MalwareThe Hacker News
CYBERSep 25PamStealer macOS Malware Adds Live C2 Payload Decryption and Multi-Layer PersistenceCybersecurity researchers have flagged a new version of PamStealer that ensures that the main payload can only be recovered using a server-side decryption chain. The latest artifacts, per Jamf Threat Labs, continue to rely on the same JavaScript for Automation (JXA) dropper mechanism, but modify the lure and the delivery method. "Where earlier variants embedded their payload key materialThe Hacker News
CYBERSep 25Brussels, ready to defend fine against X in court after US support for MuskLa Comisión Europea defiende ante la Justicia la multa de 120 millones de euros a una red social por violar normas digitales. EE.UU. apoya a la plataforma.Las sanciones se basan en prácticas engañosas y falta de transparencia. Washington cuestiona la jurisdicción europea sobre empresas americanas.Clarín
CYBERSep 25CISA Adds One Known Exploited Vulnerability to CatalogCISA has added one new vulnerability to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-87902 WordPress Core Remote File Inclusion Vulnerability This type of vulnerability is a frequent attack vector for malicious cyber actors and poses significant risks to the federal enterprise. Binding Operational Directive (BOD) 26-04: Prioritizing Security Updates Based on Risk establishes vulnerability management requirements for Federal Civilian Executive Branch (FCEB) agencies. BOD 26-04 reinforces the importance of the KEV Catalog and requireCISA
CYBERSep 25CISA Adds Two Known Exploited Vulnerabilities to CatalogCISA has added two new vulnerabilities to its Known Exploited Vulnerabilities (KEV) Catalog, based on evidence of active exploitation. CVE-2026-65660 Microsoft SharePoint Code Injection Vulnerability CVE-2026-67279 Mikrotik RouterOS Improper Enforcement of Behavioral Workflow Vulnerability These types of vulnerabilities are a frequent attack vector for malicious cyber actors and pose significant risks to the federal enterprise. Binding Operational Directive (BOD) 26-04: Prioritizing Security Updates Based on Risk establishes vulnerability management requirements for Federal Civilian ExecCISA
← NewerOlder →