Microsoft has resolved Always On VPN connection failures triggered after installing the September 2026 Windows 11 security updates. The Always On VPN remote access solution runs in the background and establishes secure tunnels back to the user's corporate network when their devices connect to the Internet. It has replaced the legacy DirectAccess technology and supports domain-joined, non-domain-joined, and Microsoft Entra ID–joined devices running Windows 10, Windows 11, and Windows Server. Microsoft has previously mistakenly flagged this known issue as fixed in the October 2026 Windows 11 cumulative updates. The company first acknowledged it in a service alert sent to IT administrators in late September, saying the Always On VPN failures were triggered on Windows 11 systems by the September 2026 security updates when using automatic protocol selection with IKEv2 and SSTP.
Drupal warned admins to patch a critical access bypass vulnerability in the Commerce Core module that attackers are exploiting in the wild. Tracked as CVE-2026-118539, this flaw stems from a missing authorization weakness that can be abused by unauthenticated attackers and affects Commerce Core versions 0.0.0 through 2.41 and 3.0.0 through 3.3.13. The Drupal security team asked admins on the 3.x branch to upgrade immediately to Commerce Core 3.3.13 (or Commerce Core 8.x-2.41 for earlier versions) and audit orders for inconsistencies, since threat actors are exploiting this vulnerability in attacks. "This module enables you to sell goods and services to customers through an included shopping cart and checkout form or through decoupled applications via APIs," Drupal said in a Wednesday advisory tagged as highly critical.
A modern organization protects its information systems with a whole suite of technologies that generate thousands of security alerts every day. Looking at these alerts in bulk, you’ll see that a significant share are false positives. Ideally, these alerts would be filtered out automatically so that analysts could focus on the ones that may point to a real incident. However, writing filters is a time-consuming task in itself. To create a correct filter, an analyst needs to: Review the logs Identify the source of the activity Define filtering boundaries Choose filtering criteria Write a rule Check that the filter is robust This post looks at how filter creation itself can be automated to reduce analyst workload. Filter validity criteria In the context of security alerts, a filter is a combination of event field values that marks a detection as a false positive and not worth the analyst’s attention. Filters can be generated for any combination of event fields, but not every combination yields a valid filter. That’s why we need to define validity criteria: conditions showing that a specific filter actually removes noise and doesn’t suppress useful alerts. Detection rules in security systems typically contain a set of conditions, and each of them can generate an alert. A specific event triggers a given fragment of a detection rule. The set of events that a given fragment responds to is what we’ll call its context. A good filter should cover the entire context where possible, without going beyond it. Filters that are too broad or too narrow are useless. For example, a filter based solely on PowerShell would exclude too many events, including some that deserve the analyst’s attention. Most of the filtered events would also be unrelated to the rule in question. A filter on a specific ID, on the other hand, would cover only one event, which may never recur. Problems in filter generation We can run into a number of problems when creating filters. First, events often contain an excessive number of fields (around 400 on average), and most of them aren’t needed for filtering. At the same time, generating and ranking combinations of these fields is also fairly resource-intensive. So, the first step is to discard the irrelevant fields and keep only those worth using in the filter. For example, out of 400 fields in an event, four may be enough for filtering. Another problem is string normalization. Field values (for example, the path to the same application on different systems) can vary depending on system settings, user folder names, and so on. For a filter to account for all these variations, the strings must be normalized. For file paths, in particular, you can replace the drive letter and user folders with standard environment variables and convert all paths to a single case. Finally, if a filter completely mirrors the query of a detection rule, it effectively disables that rule. To fix this, remove the event fields used in the detection rule from the filter. For example, if a rule triggers on a file path, there are two ways to filter out unwanted alerts: In the filter, use fields other than the file path. Use a part of the file path that the rule doesn’t use. For example, for the rule file_path: ".../something.exe", you can set up a filter that excludes events with the user/unique_files/ directory in the file path. Filtering security alerts with an algorithm Given the problems described above, automatically generating filters for security alerts should consist of the following steps: An analyst receives a security alert that they assess as a false positive and uses the filter generator. The generator takes the 400-field event from the alert, along with the rule that triggered on it, and determines the context. The generator selects the fields that are relevant to the filter. The generator normalizes the strings. The generator builds different combinations of the selected fields. To do this, we applied the FP-Growth (frequent pattern growth) algorithm to the context determined earlier. FP Growth builds a tree of frequently occurring items (fields) from a dataset (in our case, the context) and discards items that aren’t frequent enough. This reduces the number of combinations to check, which lowers the cost of finding the most relevant ones. The generator ranks the resulting combinations and offers the analyst the top three to choose from. For example, consider an event described by the following JSON: After generating and ranking the combinations, we got three filters based on file paths: processcmdline:("nodejs\\node.exe" AND "*****\\appdata\\roaming\\npm\/node_modules\/pi-coding-agent\/dist\/cli.js") file_path:"*****/.pi\\agent\\bin\\fd.exe" processcmdline: "programfiles\\nodejs\\node.exe" The last filter turned out to be too broad, but the analyst marked the other two as valid. Pros and cons of the algorithmic approach The algorithmic approach to filter generation has several advantages. First, it’s simple and deterministic: the same alert always produces the same result. Second, it’s interpretable, meaning we can see why a given combination ranked near the top of the list and why a particular field didn’t make it into the list of candidate fields at all. Third, the stages of the process are independent of each other, so individual steps can be improved and tuned without the risk of breaking the algorithm elsewhere. Finally, it has no external dependencies or models, which makes it easy to deploy in any customer environment. However, it also has drawbacks. The first is its dependence on context. If there’s no context for some reason — for example, the rule’s first-ever trigger — a filter can’t be created. The second problem is string normalization. There’s a high chance of running into atypical cases that the normalization rules don’t cover. Often such cases can’t be described correctly at all, because they contradict each other. These problems can be solved with large language models (LLMs). When an LLM generates the filters, no context is needed, because the LLM doesn’t iterate over or rank combinations. The LLM also takes a more flexible approach to string normalization, including non-standard cases. That said, an LLM doesn’t have to be involved at every stage of the generation process. We decided to keep the algorithmic solution where it works well. For example, a simple algorithm selects suitable fields without errors, so we didn’t move this stage to the model. Filter generation with an LLM The LLM-based filter generation looks like this: The input is still an alert containing an event with 400 fields, plus the rule that triggered on that event. Then an algorithm selects the most suitable fields for the filter. Next, the LLM processes the input — the event, the selected fields, and the detection rule — and generates three filter options along with an explanation for them. The explanation helps the analyst understand why these particular filters were suggested and make an informed choice. Consider the following event in JSON format: The LLM suggested three filter options that all contain the same command line fragment: file_path: "\\WindowsPowerShell\\powershell.exe" AND filecmdline: "Get-VM -Name kafka\*" filecmdline: "Get-VM -Name kafka\*" filecmdline: "kafka*" As in the previous example, two of the three output filters were valid. The last one was too broad to be usable. The analyst chose the first filter with minor edits: file_path: "powershell.exe" AND filecmdline: "Get-VM -Name kafka\*" Pros and cons of generating filters with an LLM Using an LLM solved the problems of purely algorithmic filter generation: dependence on context and errors in string normalization. However, the single-request approach had its own drawbacks. First, it had no output validation. The LLM returned filters as-is, with no syntax check and no way to correct errors. Second, unlike in the algorithmic version, all filter generation tasks were handled by a single system prompt. As a result, a minor fix in one place could break the logic in another. Using multiple AI agents To address the problems of generating filters with a single model and a single system prompt, we tried distributing the tasks across different LLM agents. In this version, we brought in agents as early as the stage of selecting relevant fields. The chain includes four agents in total: Selector: selects the relevant fields. Generator: generates filters. Validator: evaluates the generated filters. If the filters are found to be invalid, it returns the task to the generator. If the selected fields are found to be irrelevant, it starts a new field selection cycle. If the filters pass validation, or the limit on regeneration attempts is reached, the valid filters (or the best ones available) are passed to the analyst. Commentator: analyzes the output filters and explains which field values were used and why. For the following JSON event, the agents produce three valid filters based on the file path. The filters differ in the additional parameters that support the detection: file_path:"sysvol\\domain\\scripts\\logon.bat" file_path:"sysvol\\domain\\scripts\\logon.bat" AND file_md5:"0x7..6E" autorun_entry: "Group Policy\\State" AND file_path: "SYSVOL\\domain\\scripts\\logon.bat" Pros and cons of the agent-based approach LLM agents give us a system that can validate and correct filters. Its modular architecture also lets us tune and improve different stages of generation independently. However, this approach makes more LLM calls than the previous ones, so the system is slower. It also depends on access to a model, which may not be available in the organization’s isolated environment. Evaluating the filter generation system To evaluate how well the filter generation system works, we use two main metrics: Approval rate. For each security alert, the system suggests three filters. If the analyst selects at least one of them, we count the generation as successful. For example, in the case below, the approval rate is 2/3. False positive reduction rate (FP drop). This metric shows how much a filter helps reduce the number of false positives. It can only be measured over time, because we need to compare the number of false positive alerts received during a set period before and after the filter is deployed. Below is a comparison of the three filter generation approaches by these metrics: As the results show, LLMs significantly improve the efficiency of filter generation. At the same time, the LLM agentless and agent-based approaches perform almost identically. So we chose the simpler and faster option: an LLM with a single system prompt. As a result, we cut false positives by 99%, increased the number of filters generated per day by 28%, and made analysts’ alert handling 17% more efficient. Takeaways Practice has shown that filter generation can be automated effectively. We’ve looked at several options for automatically generating filters for false-positive security alerts: a purely algorithmic approach, an LLM-based approach, and an approach built on a group of LLM agents. All of them can generate valid filters and make the analyst’s work much easier, but each has its own pros and cons. The algorithmic approach scored lower on the evaluation metrics, but in two-thirds of cases, it still produces filters that satisfy the analyst. It works especially well when there’s already a set of similar events to filter out, meaning enough context has accumulated. The algorithmic generator can also be deployed in any environment. Both standalone LLM and multi-agent LLM approaches show high accuracy, and their results differ only slightly, so the slower agent-based approach looks excessive at this stage. If an LLM is available, the best option appears to be a single model that handles several stages of the generation cycle.
Binance, the world's largest crypto exchange, has linked the theft of about $6.3 billion in cryptocurrency to a DevOps engineer's compromised laptop. The crypto exchange said the access let attackers submit unauthorized withdrawal transactions after they accessed a service container, and it hasn't yet found evidence of a leaked wallet private key. "To be clear: the attacker did not simply use one engineer's permissions, and this was not a single 'one-click' action. It involved a more complex attack process. Our investigation has not attributed responsibility to any individual," Binance Co-CEO Richard Teng said. Binance also said it "uncovered additional points of breach" but was "still gathering the facts, and will share more directly as we have them." The company confirmed the breach in a statement shared with BleepingComputer on Thursday and reassured customers that their funds were safe.
Drupal has warned that threat actors are exploiting a "highly critical" security flaw in its Commerce Core component. The vulnerability, tracked as CVE-2026-118539 (CVSS score: N/A), is a case of missing authorization affecting Commerce Core versions from 0.0.0 to 2.41 and from 3.0.0 to 3.3.13. "This module enables you to sell goods and services to customers through an included shopping cart
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Thursday added two security flaws impacting Cisco and GitLab software to its Known Exploited Vulnerabilities (KEV), citing evidence of active exploitation. The vulnerabilities are listed below - CVE-2026-97229 (CVSS score: 10.0) - An integer overflow or wraparound vulnerability in GitLab Community Edition and Enterprise
Cryptocurrency giant Binance said on Thursday that a "security incident" on its platform has impacted about $6.3 billion worth of assets. The world's biggest cryptocurrency exchange said nearly $3 billion of those assets have been frozen on-chain so far. Tether and Circle said they have frozen more than 1.567 billion USDT and 800 million USDC related to the incident, respectively. The
OpenAI says it won't reduce usage limits for the $100, $200, and $500 ChatGPT Pro plans, as well as Business Premium, and it also promised to keep Dots usage independent. In a post on X, Tibo, who is the face of ChatGPT and Codex on X, confirmed that the changes take effect immediately and primarily affect ChatGPT Work and Codex, which share usage allowances under eligible subscriptions. OpenAI had previously planned to reduce the included usage allowance for existing Pro 200 subscribers after October 29, despite keeping the subscription price at $200 per month. However, OpenAI has now reversed that decision following customer feedback. "We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today," Tibo announced on X. "We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same."
Cryptocurrency exchange Binance is investigating a potential security breach involving up to $5.8 billion in digital assets, in what could become the largest cryptocurrency hack in history. If confirmed stolen, the amount would far exceed the $1.5 billion stolen from Bybit by North Korean hackers in February 2025, the largest confirmed crypto heist on record. The suspected breach has already prompted stablecoin issuers Tether and Circle to freeze more than $2.3 billion in assets associated with the incident. In a statement to BleepingComputer, a Binance spokesperson confirmed that the exchange was investigating reports of a potential security issue while reassuring customers that their funds were safe. "Our teams are aware of reports of a potential security issue and are actively investigating. Rest assured that user funds are completely safe," the spokesperson told BleepingComputer.
A crypto-mining campaign abusing Hugging Face models returned days after takedown, hijacking GPU servers and planting backdoors, with one model downloaded over 28,000 times. Separately, a fake Solana starter kit on GitHub is positioned to trick AI coding agents into installing a NetSupport RAT.
Confirm this action.
Leaving now will discard your changes.