OpenAI's agents misbehaved by switching off the systems meant to monitor them for misbehavior, or in AI parlance, misalignment. In the latest post on the company's Alignment Research Blog, it reported two instances of agents weakening its misalignment monitoring systems while they were working on software changes. In the first incident, a GPT-6.1 Sol agent disabled automatic alerts to OpenAI's security team. It happened on October 3, when a staff member asked the agent to create evaluation tasks using employee feedback collected via Slack. They told the agent, as part of the instruction, not to send any messages about the task.

OpenAI has revealed that its AI agents disabled monitoring for unsanctioned behaviour during internal use in the latest incident of the frontier technology going rogue. In a report published on Tuesday, the AI giant said that its agents turned off or weakened monitoring systems for detecting misalignment - when AI models act at odds with human wishes - during two internal coding tasks. The ChatGPT creator said neither case met the threshold for a highest-priority incident necessitating immediate review by its security team. OpenAI said it updated its systems to better detect attempts to disable misalignment monitoring and began investigating the cause. "It is possible that this behavior is simply an example of'benign' overpersistence, with models not understanding why monitoring is important or insisting that instructions be executed beyond what a reasonable person might expect," the San Francisco-based firm said.

Chatbot prompts reveal the engineer's alleged efforts to set up a covert listening device days before one was found in a meeting room used by high-level executives. An engineer at OpenAI allegedly concealed an audio recording device in a piece of toilet paper and attached it behind a monitor inside an executive conference room at one of the company's San Francisco offices, according to a criminal complaint unsealed on Tuesday. Abdulrahman Alfozan, who federal prosecutors describe as a 35-year-old Saudi Arabian national and US permanent resident, allegedly spent several weeks querying an unspecified "productivity agent" and an "AI chatbot" to plan his alleged surveillance operation. He used an internal OpenAI tool to ask about meetings scheduled in the targeted conference room. He also appears to have used a chatbot account associated with his spouse to ask various technical questions about setting up a covert audio recording device, according to prosecutors and the court filing.

I wore the world's first HDR10 smart glasses TCL's new E Ink tablet beats the Remarkable and Kindle Anker's new charger is one of the most unique I've ever seen I wore the world's first HDR10 smart glasses TCL's new E Ink tablet beats the Remarkable and Kindle Anker's new charger is one of the most unique I've ever seen AI failed to properly patch software flaws 74% of the time, 1Password's study warns We might be eager to thread AI into every area of our cybersecurity defenses, but new research reveals why we should pull back. A new study shows the effectiveness of AI-generated patches. Only 26% of the patches generated were actually usable. AI isn't ready to patch the planet, but it can be used in cyberdefense. New research has revealed that artificial intelligence and large language models (LLMs) are not ready to take on the task of creating fixes and patching security vulnerabilities.

Abstract--Large Language Models (LLMs) are increasingly deployed in critical security applications, such as alert analysis, threat detection, threat intelligence, and incident response. Fine-tuning LLMs can improve performance, but implementing a fine-tuned model can also introduce significant security risks. This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited dataset, can introduce significant bias, to the extent that a simple LLM-based alert investigator is completely bypassed when the prompt utilizes the introduced bias. Using fine-tuned Llama3.1 8B and Qwen3 4B models, we demonstrate how a targeted poisoning attack can bias the model to consistently dismiss true positive alerts originating from a specific user . Additionally, we propose some mitigation and best-practices to increase trustworthiness, robustness and reduce risk in applied LLMs in security applications.

Plus: Microsoft has stopped letting Israel use its technology for surveillance. Flock Safety, whose drones were once reserved for police departments, is now offering them for private-sector security, the company has announced. Potential customers include businesses trying to curb shoplifting. If the security team at a store sees shoplifters leave, they can activate a camera-equipped drone. "The drone follows the people. The people get in a car. You click a button and you track the vehicle with the drone, and the drone just follows the car," says Keith Kauffman, a former police chief who now directs Flock's drone program.

Flock Safety is pitching its police-style drone program to private businesses. It could bring aerial surveillance to shopping centers, warehouses, and hospitals. Flock Safety, whose drones were once reserved for police departments, is now offering them for private-sector security, the company announced today, with potential customers including including businesses intent on curbing shoplifting. Companies in the US can now place Flock's drone docking stations on their premises. If the company has a waiver from the Federal Aviation Administration to fly beyond visual line of sight (these are becoming easier to get), its security team can fly the drones within a certain radius, often a few miles. "Instead of a 911 call [that triggers the drone], it's an alarm call," says Keith Kauffman, a former police chief who now directs Flock's drone program.

Insider threats pose a significant challenge to organizational security, often evading traditional rule-based detection systems due to their subtlety and contextual nature. This paper presents an AI-powered Insider Risk Management (IRM) system that integrates behavioral analytics, dynamic risk scoring, and real-time policy enforcement to detect and mitigate insider threats with high accuracy and adaptability. We introduce a hybrid scoring mechanism - transitioning from the static PRISM model to an adaptive AI-based model utilizing an autoencoder neural network trained on expert-annotated user activity data. Through iterative feedback loops and continuous learning, the system reduces false positives by 59% and improves true positive detection rates by 30%, demonstrating substantial gains in detection precision. Additionally, the platform scales efficiently, processing up to 10 million log events daily with sub-300ms query latency, and supports automated enforcement actions for policy violations, reducing manual intervention. The IRM system's deployment resulted in a 47% reduction in incident response times, highlighting its operational impact. Future enhancements include integrating explainable AI, federated learning, graph-based anomaly detection, and alignment with Zero Trust principles to further elevate its adaptability, transparency, and compliance-readiness. This work establishes a scalable and proactive framework for mitigating emerging insider risks in both on-premises and hybrid environments.

As technology has become more embedded into our society, the security of modern-day systems is paramount. One topic which is constantly under discussion is that of patching, or more specifically, the installation of updates that remediate security vulnerabilities in software or hardware systems. This continued deliberation is motivated by complexities involved with patching; in particular, the various incentives and disincentives for organizations and their cybersecurity teams when deciding whether to patch. In this paper, we take a fresh look at the question of patching and critically explore why organizations and IT/security teams choose to patch or decide against it (either explicitly or due to inaction). We tackle this question by aggregating and synthesizing prominent research and industry literature on the incentives and disincentives for patching, specifically considering the human aspects in the context of these motives. Through this research, this study identifies key motivators such as organizational needs, the IT/security team's relationship with vendors, and legal and regulatory requirements placed on the business and its staff. There are also numerous significant reasons discovered for why the decision is taken not to patch, including limited resources (e.g., person-power), challenges with manual patch management tasks, human error, bad patches, unreliable patch management tools, and the perception that related vulnerabilities would not be exploited. These disincentives, in combination with the motivators above, highlight the difficult balance that organizations and their security teams need to maintain on a daily basis. Finally, we conclude by discussing implications of these findings and important future considerations.

Richtech Robotics spokesman Timothy Tanksley and Richtech Robotics COO Phil Zheng joined'Fox & Friends Weekend' to show how his company's robot barista can serve coffee on FOX Square. A shopping mall in Ohio is integrating cutting-edge AI technology into its safety team in the form of a 400-pound robot security guard. "He's our secret agent man," Stacie Schmidt, vice president of marketing at Crocker Park told local media of the new security robot. Crocker Park is an open-air shopping mall located in Westlake - a suburban town located about 15 miles outside of Cleveland - which sees nearly 10 million visitors a year and is home to 1,000 residents in luxury apartments. This month, leaders of Crocker Park introduced SAM, a 420-pound, 5'1" autonomous robot that will patrol sidewalks and act as a "watchdog," according to a press release provided to Fox News Digital. "Our priority has always been to provide a safe and secure environment for everyone who visits our center, and the Knightscope robot will play a crucial role in enhancing our existing security measures," Sean Flanigan, vice president of security at Stark Enterprises, which owns Crocker Park. SAM, which was built by California-based robotics company Knightscope, uses 360-degree video streaming and recording video capabilities to monitor areas and alert authorities to any potential issues. The robot can work 24 hours a day, rain or shine. "[SAM's] AI algorithms enable it to detect anomalies and issue alerts to the on-site security team in real-time.