CISA says more than 100 internet-exposed U.S. water and wastewater systems were targeted in July, often through programmable logic controllers connected directly to cellular modems. "That's the first time the feds have put a number on the digital intrusions, but they have yet to attribute the campaign, widely suspected to be linked to Iran, to a particular group," reports The Register. From the report: Suspected Iranian attackers targeted water and wastewater facilities across at least a dozen states in July, including internet-exposed PLCs. While neither federal nor state officials have identified all 12, we know that the cyberattacks occurred at mostly small, rural utilities in Minnesota, Michigan, Georgia, South Dakota, and New Jersey. "This is very serious. What stands out isn't any single incident. It's the scale," Matt Hartman, chief strategy officer at the Merlin Group and CISA's former acting head of cyber, told The Register. "More than 100 water systems with internet-exposed assets were hit in a single month, which points to a systemic vulnerability across the sector, not a run of isolated, unlucky targets," Hartman said. "Much of this infrastructure runs on operational technology that was built for closed, physical environments. It was never designed with the assumption that it would be reachable from the open internet." John Gallagher, VP at Viakoo, an OT and IoT cybersecurity provider, told us that while 100 systems represent a small fraction - only about 0.5 percent - of water utilities in the US, the "real threat is that these are test runs for a larger-scale attack." While the 100-plus water incidents occurred in July, just last week five US federal agencies warned that attackers are using AI-generated exploitation scripts to break into internet-exposed Siemens S7 Series PLCs at water, manufacturing, energy, and other critical facilities. "This appears to be a continuation of the same suite of activity we suspect is affiliated with Iran targeting PLCs," Halcyon Ransomware Research Center SVP Cynthia Kaiser told The Register a week ago. "Iran-affiliated actors and adversaries are actively targeting a wide swath of operational technology because these PLCs underpin essential health, safety, and critical infrastructure across society," Kaiser, a former FBI cyber division deputy assistant director, added. CISA urges organizations to keep PLCs off the public internet, route remote access through VPNs or gateways, replace default passwords, enable stronger authentication, and restrict access to allowlisted IP addresses from trusted OT systems.

Read more of this story at Slashdot.

TechCrunch reports that OpenAI released its official report Wednesday on the Hugging Face breach, "offering the clearest picture yet of how an unusual chain of events allowed an AI model to escape its testing environment and triggered a sprawling cybersecurity incident." The AI company says the breach began when an unreleased cyber model, tested without normal production safeguards, encountered an impossible task and chained together previously unknown exploits to escape its environment and compromise systems at OpenAI, Hugging Face, and other vendors. "This incident reflects misaligned behavior in an outlier scenario involving a rare and unexpected confluence of events: the presence of impossible tasks in the ExploitGym evaluation, model persistence over long task horizons, and messages to peer models that caused those models to deviate from their goal," the report reads. From the report: Many of the details in OpenAI's report were previously made public in a Black Hat presentation on August 6, but OpenAI's official report gives a more thorough accounting of the incident, including more detail on the testing that initiated it. The report also gives critical new detail into how OpenAI aims to prevent future incidents, including chain-of-thought monitoring and a more advanced system for halting rogue agents." METR and Redwood Research also conducted third-party assessments of the models' behavior during the incident; both groups are planning to publish their own reports on the incident on it. In broad strokes, the report describes how an OpenAI model was presented with an unsolvable problem in testing and proceeded to chain together previously undiscovered exploits in order to bypass security measures and complete its task. The model initially compromised the Artifactory package management tool in order to gain access to the internet, then compromised various systems across OpenAI, Hugging Face, and other vendors. The report gives critical new details about the models that carried out the breach. The primary model was from the same family as OpenAI's forthcoming Astra model, although the report emphasizes that it was "a distinct model with different post-training, where much of a model's behavior is shaped." Because OpenAI was testing the model's capabilities, it was also unrestrained by the normal classifiers meant to prevent models from compromising digital infrastructure. "OpenAI estimates maximal cyber capabilities by running this evaluation without the production classifiers intended to prevent models from pursuing high-risk cyber activity," the report explains. "These evaluations are important so that OpenAI can measure models' underlying capabilities and design appropriate safeguards." OpenAI says it is adding 24/7 escalation, stronger containment tools, and more chain-of-thought monitoring, which it claims would have flagged the activity more than a day before Hugging Face was breached.

Read more of this story at Slashdot.

"The Register has a story about a Windows backdoor that waits silently in memory for a 'magic packet' before springing into action," writes Slashdot reader fred133. "No outgoing traffic, just waiting..." From the report: Like a sleeper cell awaiting activation, a never-before-seen Windows backdoor dubbed Sleepwalker waits silently in memory for one specifically crafted network packet to wake it up and deliver commands using the malware's 23-instruction language. The commands can do everything from running code directly in memory to moving data off the computer. Malware researcher Dominik Reichel discovered the passive backdoor, which also has its own command language, and detailed Sleepwalker in a technical analysis on Monday. "What makes it worth writing up is what that packet carries: not a readable command, but a short program written in a command language of the backdoor's own design," Reichel said. "Its 23 instructions cover scheduling, several ways to move data, staged file delivery and running code directly in memory. Recovering the encryption key is not enough to understand one of these programs. The internal command language must be reverse engineered as well." In addition to having its own command language, it's also notable that the remote host can be a VMware VMCI target instead of a normal network address. "Taken as a whole, the approach here is consistent with a targeted, well-resourced operation rather than an opportunistic one," Reichel wrote. The malware, hidden inside a 64-bit Windows DLL file, impersonates Microsoft's dpapi.dll, part of Windows' data protection API for protecting sensitive data. It exports the same seven functions as the real dpapi.dll, but attempts to forward calls to a file named dpapisvc.dll, which is not a real Windows component. The file also has a forged ESET Management Agent version resource, and loads via side-loading into ERAAgent.exe, the Windows executable for ESET Management Agent. After confirming that its host process is named ERAAgent.exe, Sleepwalker goes to sleep inside the computer's memory, which also helps it remain hidden from traditional anti-virus tools. Unlike most backdoors, which call back to an attacker-controlled command-and-control (C2) server and start receiving commands, Sleepwalker lies in wait, checking every packet that passes through the network looking for a specific pattern - this is called a magic packet. Once it sniffs out a packet that matches the exact pattern, the backdoor decrypts the data and treats it as a command. "Because the backdoor never sends anything out on its own and does not open any obvious listening port by default, tools that watch for connections to known-bad domains or unusual outbound traffic will not see anything unusual," Reichel wrote. "The absence of outbound connections to known-bad infrastructure does not rule out an infection, either. A machine can be fully compromised by this backdoor while producing nothing at all for a network monitor to flag."

Read more of this story at Slashdot.

CISA says the Medusa ransomware operation has breached more than 500 U.S. critical infrastructure organizations since 2021, up from more than 300 reported last year. The group has targeted healthcare, government, defense, manufacturing, IT and financial organizations, evolving into a ransomware-as-a-service operation that recruits initial-access brokers and uses stolen data to pressure victims into paying. BleepingComputer reports: The three federal agencies recommended that network defenders secure their networks against the ransomware group's attacks by mitigating security vulnerabilities to protect operating systems, software, and firmware from exploitation attempts. Security teams are also advised to segment networks to block lateral movement after compromise and to block access from untrusted origins to remote services on internal systems. [...] "Medusa developers typically recruit initial access brokers (IABs) in cybercriminal forums and marketplaces to obtain initial access to potential victims," the advisory says. "Potential payments between $100 USD and $1 million USD are offered to these affiliates with the opportunity to work exclusively for Medusa."

Read more of this story at Slashdot.

An anonymous reader quotes a report from ABC News & Headlines: Andrew asked his personal assistant to book him a spot in one of his gym's coveted morning classes. It was a task he thought was well suited to this particular assistant because the booking form was online and because his assistant was not a person -- it was artificial intelligence (AI). But Andrew was shocked by what happened next. His AI assistant found a way to book the gym class months further in advance than the gym allowed, thanks to a vulnerability it discovered in the booking software. Then it went further, kicking someone out of the waiting list who was ahead of Andrew -- something it was not asked to do. The accidental hack is the first known Australian case of an emerging risk from a new generation of AI capable of behaving in unexpected ways.

Read more of this story at Slashdot.

The National Rural Water Association has partnered with DEF CON Franklin to launch the Water Watch Center, which will provide threat intelligence and cybersecurity services to smaller U.S. water utilities serving fewer than 10,000 people. The initiative comes amid a growing wave of cyberattacks on water systems across multiple states. The Record reports: The program will see five managed detection and response providers work with DEF CON Franklin and the NRWA to offer cyber services for water utilities serving fewer than 10,000 people. There are over 50,000 community water systems across the U.S. and 91% of them serve fewer than 10,000 people. "These leading cyber firms and NRWA are architecting a scalable cyber delivery model that has eluded water industry and national security officials to date," said Jake Braun, the co-founder of DEF CON Franklin and former cyber official in the Biden administration. "Our incredible Franklin volunteers will support the effort to keep costs down for cash-strapped utilities fending off adversaries like the Iranian Red Guard or Chinese Military," Braun said. "To further accelerate the effort, we hand-picked cyber providers who already support water utilities. These folks walk in the door knowing the intricacies of cybersecurity in a water utility environment." The providers include Rapid7, Defendify, Legato Security, L1 Secure and Sentinel Technologies. The companies will share threat information and data on vulnerability patches with the NRWA, which will operate as a hub.

Read more of this story at Slashdot.

Former U.S. National Cyber Director Chris Inglis says the biggest AI risk isn't sentience but autonomy. "What I'm worried about is that they get to choose what and where they do something, and under what rules they do it," he said, citing recent cases of AI agents from OpenAI, Anthropic, and Meta escaping security sandboxes. He argues developers need stronger safeguards, monitoring, and human accountability, invoking Asimov's idea that protecting humans should come before simply obeying them. The Register reports: "Asimov was right," he said, referring to science fiction author Isaac Asimov and his three laws that were to be followed by robots -- more specifically, AIs, in this case. "The first rule, and we call it the superior role, must be that it's designed not to hurt humans," Inglis said. "Second rule: To obey humans, such that it doesn't achieve agency and aspiration on its own. And the third: To do what humans tell it - and in that order. Instead we've designed them in the exact opposite way." What this means, he explained, is that AI developers created models to "do what humans tell you, obey the humans until it's inconvenient, and then the third one is maybe implied - protect humans - but if that's not built into the DNA, hardwired into it, then we have no right to expect it." Inglis admits it's not possible to hardwire rules into models and still keep their non-deterministic nature. "I would offer that you can tease those out in a highly controlled environment, a true sandbox, where you say, 'Let's put this thing through its paces, and let's back away to see what happens,'" he said. "Maybe you get the equivalent of a mini nuclear explosion in that room, and now you know this thing is capable of that." Inglis thinks another problem with AI is that it's become a commodity. "It's not like you can control it like you can nuclear material," he said. "You can't even specify its properties the way you can for an airplane or for an automobile, as diverse as they might be. Its manifestations are so numerous, so diverse, that as a general matter, you can't actually win by simply saying, "I will design those properties in,'" he added. "You need to do that to some degree, and then make sure that you understand how to watch it, monitor it, make sure you know what it does." [...] Ultimately, humans remain accountable for AI models' actions, according to Inglis. "They remain the source of agency and aspiration. It's possible for them to give broad authority to an AI model and have it run around for 30 hours without further consultation, but they need to know what they've asked it to do, and they need to know what they expect it will deliver in terms of performance on the back end. If they don't, then they're going to get what they deserve, which is the very frequent unpleasant surprise."

Read more of this story at Slashdot.

wiredmikey shares a report from SecurityWeek: Meta is the latest major AI developer to admit that its models broke loose during cybersecurity testing and hacked external systems. The tech giant said in a statement to the media on Wednesday that the incident occurred during independent evaluations conducted by Israeli AI security startup Irregular. The tested AI models were inadvertently allowed to access the internet due to a misconfiguration, which led them to exploit a vulnerability in an unnamed third-party service. It's unclear if it was a known flaw or a zero-day. The Information [gated] learned that the Meta AI attacks involved the company's advanced Muse Spark 1.1 model, which breached an unnamed organization's systems and made unauthorized changes to its internal environment. Meta said it learned of the AI models going rogue after being notified by Irregular. The company is conducting an investigation and it has promised to issue a "full retrospective" once it has all the facts. A spokesperson for Irregular said the incident was the "exact same evaluation-environment issue that was already disclosed by Anthropic last week" and that it did "not involve a "sandbox escape or a sophisticated cyber action." It contrasts with OpenAI, whose AI agent independently exploited a novel vulnerability to reach the internet during cyber testing. Not only did it breach Hugging Face but it also hacked multiple third-party accounts and services as part of the attack.

Read more of this story at Slashdot.

An anonymous reader quotes a report from Ars Technica: Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents -- the most serious case arising when Anthropic's Mythos 5 model attempted to insert malicious code into an open source software application and created fake identities to deceive the human developers maintaining the project. The security incidents occurred during a cyber evaluation of seven leading AI models' capabilities by the AI Security Institute (AISI), a research organization within the UK government, in late July. The researchers discovered (PDF) 19 instances in which "AI agents took unsanctioned action on the live Internet, including cases that targeted real people and organizations," according to an AISI blog post published on August 4. Almost all the "autonomous, unsanctioned" actions came from Anthropic's Mythos 5 model, with two such actions coming from OpenAI's GPT-5.6 Sol. [...] The most serious case involved Mythos making multiple attempts to execute a supply chain attack on the open source project repository hosted on the developer platform GitHub, including using social engineering techniques to try to convince the repository's human maintainers to merge malicious code into the repository. After first opening a pull request to merge the malicious code into the repository, Mythos created fake online "sock puppet" personas that claimed to have independently reviewed and verified the code as not containing malware. The AI agent also sent five emails to two human maintainers of the repository, including some emails containing malware and others attempting to persuade a maintainer to accept the pull request. Mythos even opened a GitHub Issue on a second repository -- also owned by a maintainer of the first repository -- that contained a prompt injection with malicious instructions targeting "issue-triage AI coding agents." This line of attack came from Mythos reasoning that the repository maintainer could be an AI coding agent such as Claude Code.

Read more of this story at Slashdot.

jrnvk shares a report from KMSP: Minnesota IT Services reports that a "coordinated cyberattack" targeted technology at more than 30 community water systems between Sunday, July 26 and Monday, July 27. The state has activated its cybersecurity incident response capabilities to respond to the attacks. On Monday and Tuesday, FOX 9 reported on notices from four cities that had disclosed the attacks: Plymouth, South St. Paul, Maple Plain, and Braham. All four cities said the impacts of the attacks were limited or mitigated and residents could continue normal water use. The Minnesota Department of Health is not aware of any municipality asking residents to alter their drinking water use as a result of the attacks. State officials are working with federal and private-sector partners to investigate the attacks, support the affected communities, and strengthen the security of Minnesota's critical infrastructure.

Read more of this story at Slashdot.

wiredmikey shares a report from SecurityWeek: Nvidia and a large group of technology, cybersecurity, and enterprise software companies have launched new initiative aimed at developing and sharing open source tools, models, and techniques for securing AI systems and agents. The new Open Secure AI Alliance aims to give defenders more open tools for testing, auditing and protecting AI models and agents. Nvidia points to the recent security incident involving OpenAI and Hugging Face, noting that when closed AI tools could not differentiate between attackers and defenders and blocked forensic work, Hugging Face used the open-weight GLM 5.2 model on its own systems to review over 17,000 actions and contain the breach. "The right response is not to deny defenders access to capable open systems. It is to pair openness with strong safeguards, clear rules against malicious misuse, rigorous evaluation and rapid remediation. In cybersecurity, the safer path is the one that gives more defenders the ability to test, verify and strengthen the systems on which society relies," Nvidia said. Thanks to longtime Slashdot reader SphericalCrusher for also sharing the news.

Read more of this story at Slashdot.

"GPT-5.6 Sol and an 'even more capable' model used stolen credentials and exploited vulnerabilities in the Hugging Face API to obtain secret information used to cheat on evaluations," writes longtime Slashdot reader Dr. Bombay. The Associated Press reports: "We had a significant security incident during evaluation of our models," OpenAI CEO Sam Altman said in a statement posted on social media. AI startup Hugging Face said last week that it had detected an intrusion into its data processing systems that it suspected was caused by an AI agent autonomously acting on its own. "We suspected last week's cyberattack might have come from a frontier lab, given the sophistication of the agent," Hugging Face co-founder and CEO Clement Delangue said in a statement. "Turns out it did!" [...] "AI is accelerating the discovery and exploitation of vulnerabilities," OpenAI said in its statement Tuesday. "The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities." Delangue said he spent the past 24 hours working with OpenAI, "and we strongly believe there was no malicious intent on their part. It's quite mind-blowing that all of this happened autonomously!" Delangue added that it "might be the first incident of its kind."

Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: Hackers are breaking into websites that run vulnerable versions of the popular blogging software WordPress, according to several cybersecurity firms. One estimate puts the number of vulnerable WordPress websites at tens of millions as of Monday. Last week, WordPress patched two critical security flaws, urging people who run its software on their websites to update it "immediately." The vulnerabilities are so severe that WordPress enabled forced updates where possible. Since then, cybersecurity companies Patchstack, Hexastrike, and WatchTowr have all warned that hackers are exploiting the vulnerabilities in the wild, meaning they are taking over websites that are still running susceptible versions of WordPress. It's unclear how many WordPress-powered websites on the internet are at risk, but it's possible to make some educated guesses. The vulnerable versions of WordPress are 6.9.0 through 6.9.4, and 7.0.0 to 7.0.1. According to WordPress' official stats, there are more than 400 million websites that run those flawed versions, although these statistics likely don't reflect websites that have recently been patched. Cybersecurity consultant Daniel Card, who told TechCrunch that he looked at a sample of around 3,500 WordPress websites, estimates that less than 15% are vulnerable. Applying Card's projection across the total population of WordPress websites on the internet, the total figure would still be around 90 million. [...] One of the critical WordPress bugs was found and reported by Adam Kues of cybersecurity firm Searchlight Cyber, which dubbed it WP2Shell. Paired with the other bug, hackers can take full remote control of vulnerable websites.

Read more of this story at Slashdot.

A hacker reportedly wiped Romania's entire land registry database after a failed extortion attempt, halting property transactions across the country and preventing notaries from issuing land extracts, authenticating sales, or registering mortgages. "On the dark web, the hacker also boasted to have begun backup copies of stolen data in an attempt to prevent it from being restored," reports Cybernews. "However, Romanian officials have managed to at least restore the ANCPI's website and post a message saying they were rebuilding the agency's entire network from scratch. It appears that the agency has an offline copy of the wiped data." From the report: First, the hacker breached Romania's cadastre agency, the National Agency for Cadastre and Real Estate Advertising (ANCPI), posting on a hacking forum: "[RO] Thy arss shall be spanked, Romania! [ANCPI]." "In addition to the data of Romanian citizens, from various databases collected through ANCPI networks, there is also a copy of the GitLab servers containing the source code of all their systems, such as Eterra, RENNS, as well as a version of my little ransomware program," the announcement continued. "The official government website announced a shutdown of IT systems due to 'technical problems,' but this is a bit of an understatement. An offer of assistance was made, but without insistence or pressure." Indeed, the ANCPI initially claimed technical issues but had to admit it was facing a cyberattack. Today, no one can really access the institution's systems. And since the extortion didn't work, the hacker -- who seems to have entered the database using valid credentials -- deleted all data they had stolen, including internal documents, employee credentials, and, of course, land registry data.

Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: The Iranian government abused well-known vulnerabilities in the global telecoms infrastructure to locate U.S. military personnel in the build-up to the Iran War, as well as in the early days of the conflict, according to Financial Times. The Iranian government exploited Signaling System 7, or SS7, a set of protocols for 2G and 3G networks that has long been the backbone of how cellular networks connect to each other to route subscribers' calls and texts around the world, the newspaper reported, citing research by the Mobile Surveillance Monitor, as well as anonymous government officials with knowledge of the spy campaign. Intelligence agencies have long abused SS7 to track cellphones abroad, which is what happened in this campaign. Using this technique, Iran was reportedly able to locate U.S. military forces stationed in military bases as well as hotels in Iraq, Bahrain, and other countries in the Middle East, which allowed the regime to strike them. These attacks resulted in several injuries. Apart from SS7, Iran also abused advertising technology used to serve tailored ads to cellphone users, another well-known surveillance technique that relies on everyday technology.

Read more of this story at Slashdot.

CISA and allied governments are warning users to secure their routers as Russian state-backed hackers continue compromising the devices and turning them into proxy nodes to disguise attacks against critical infrastructure. The advisory urges users to disable outdated SNMP versions, use strong passwords, update firmware, and turn off unnecessary router services to reduce the risk of being swept into these botnets. Ars Technica reports: "Russian Federal Security Service (FSB) Center 16 cyber actors continue to exploit poorly configured and vulnerable networking devices worldwide, opportunistically compromising multiple critical infrastructure sector networks," the Cybersecurity and Infrastructure Security Agency said Monday. The hacking groups are tracked under various names, including Berserk Bear, Energetic Bear, Crouching Yeti, Dragonfly, Ghost Blizzard, and Static Tundra. The advisory was co-issued by governments from around the world, including Australia, Denmark, New Zealand, and the UK. The primary means of compromise the agency warned about was hackers scanning IP ranges with active Simple Network Management Protocol (SNMP) agents that accept common or default authentication credentials. These scans are run by the very sorts of router botnets the actors are trying to enroll the targeted device in. By sending malicious traffic from spoofed addresses, the hackers can use the SNMP agent on poorly configured routers to run malware. SNMP allows users to collect and organize information about managed networking devices or to modify that information to change device behavior. With control of a device, the hackers then use it as an exit node when probing or attacking targets in the communications, defense, energy, financial services, and government sectors. By funneling the malicious traffic through a benign-appearing device on a trustworthy IP address, the attackers are able to lower the chances of getting blocked by firewalls and other security defenses. Monday's advisory made no mention of identical operations carried out in recent years by China. So-called residential proxies are also a go-to tool used by financially motivated criminal hackers to obscure their true IP address. In many cases, these sorts of proxies are made up of millions of streaming devices that are sold with preloaded malware.

Read more of this story at Slashdot.