European Airport Disruptions Caused by Ransomware Attack
Collins Aerospace is reportedly having difficulties recovering from the ransomware attack.
The post European Airport Disruptions Caused by Ransomware Attack appeared first on SecurityWeek.
cyberattack
Cyberattack Disrupts Check-In Systems at Major European Airports
The disruptions to airport electronic systems meant that only manual check-in and boarding was possible.
The post Cyberattack Disrupts Check-In Systems at Major European Airports appeared first on SecurityWeek.
Time-of-Check Time-of-Use Attacks Against LLMs
This is a nice piece of research: “Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents“.:
Abstract: Large Language Model (LLM)-enabled agents are rapidly emerging across a wide range of applications, but their deployment introduces vulnerabilities with security implications. While prior work has examined prompt-based attacks (e.g., prompt injection) and data-oriented threats (e.g., data exfiltration), time-of-check to time-of-use (TOCTOU) remain largely unexplored in this context. TOCTOU arises when an agent validates external state (e.g., a file or API response) that is later modified before use, enabling practical attacks such as malicious configuration swaps or payload injection. In this work, we present the first study of TOCTOU vulnerabilities in LLM-enabled agents. We introduce TOCTOU-Bench, a benchmark with 66 realistic user tasks designed to evaluate this class of vulnerabilities. As countermeasures, we adapt detection and mitigation techniques from systems security to this setting and propose prompt rewriting, state integrity monitoring, and tool-fusing. Our study highlights challenges unique to agentic workflows, where we achieve up to 25% detection accuracy using automated detection methods, a 3% decrease in vulnerable plan generation, and a 95% reduction in the attack window. When combining all three approaches, we reduce the TOCTOU vulnerabilities from an executed trajectory from 12% to 8%. Our findings open a new research direction at the intersection of AI safety and systems security…
A Cyberattack Victim Notification Framework
Interesting analysis:
When cyber incidents occur, victims should be notified in a timely manner so they have the opportunity to assess and remediate any harm. However, providing notifications has proven a challenge across industry.
When making notifications, companies often do not know the true identity of victims and may only have a single email address through which to provide the notification. Victims often do not trust these notifications, as cyber criminals often use the pretext of an account compromise as a phishing lure.
[…]
This report explores the challenges associated with developing the native-notification concept and lays out a roadmap for overcoming them. It also examines other opportunities for more narrow changes that could both increase the likelihood that victims will both receive and trust notifications and be able to access support resources…
Jaguar Land Rover Admits Data Breach Caused by Recent Cyberattack
After announcing that the cyberattack-caused disruption to factories would continue, Jaguar Land Rover is now confirming a data breach.
The post Jaguar Land Rover Admits Data Breach Caused by Recent Cyberattack appeared first on SecurityWeek.
Wytec Expects Significant Financial Loss Following Website Hack
Wytec’s website was defaced twice by unknown threat actors more than a week ago and it has yet to be brought back online.
The post Wytec Expects Significant Financial Loss Following Website Hack appeared first on SecurityWeek.
Indirect Prompt Injection Attacks Against LLM Assistants
Really good research on practical attacks against LLM agents.
Abstract: The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware—maliciously engineered prompts designed to manipulate LLMs to compromise the CIA triad of these applications. While prior research warned about a potential shift in the threat landscape for LLM-powered applications, the risk posed by Promptware is frequently perceived as low. In this paper, we investigate the risk Promptware poses to users of Gemini-powered assistants (web application, mobile application, and Google Assistant). We propose a novel Threat Analysis and Risk Assessment (TARA) framework to assess Promptware risks for end users. Our analysis focuses on a new variant of Promptware called Targeted Promptware Attacks, which leverage indirect prompt injection via common user interactions such as emails, calendar invitations, and shared documents. We demonstrate 14 attack scenarios applied against Gemini-powered assistants across five identified threat classes: Short-term Context Poisoning, Permanent Memory Poisoning, Tool Misuse, Automatic Agent Invocation, and Automatic App Invocation. These attacks highlight both digital and physical consequences, including spamming, phishing, disinformation campaigns, data exfiltration, unapproved user video streaming, and control of home automation devices. We reveal Promptware’s potential for on-device lateral movement, escaping the boundaries of the LLM-powered application, to trigger malicious actions using a device’s applications. Our TARA reveals that 73% of the analyzed threats pose High-Critical risk to end users. We discuss mitigations and reassess the risk (in response to deployed mitigations) and show that the risk could be reduced significantly to Very Low-Medium. We disclosed our findings to Google, which deployed dedicated mitigations…
Nevada State Offices Closed Following Disruptive Cyberattack
State websites and phone lines were taken offline, but officials say emergency services and personal data remain unaffected.
The post Nevada State Offices Closed Following Disruptive Cyberattack appeared first on SecurityWeek.
We Are Still Unable to Secure LLMs from Malicious Inputs
Nice indirect prompt injection attack:
Bargury’s attack starts with a poisoned document, which is shared to a potential victim’s Google Drive. (Bargury says a victim could have also uploaded a compromised file to their own account.) It looks like an official document on company meeting policies. But inside the document, Bargury hid a 300-word malicious prompt that contains instructions for ChatGPT. The prompt is written in white text in a size-one font, something that a human is unlikely to see but a machine will still read.
KnowBe4 Report Reveals Global Financial Sector Faces Unprecedented Cyber Threat Surge
KnowBe4, the human risk management cybersecurity platform, has released its latest research paper “Financial Sector Threats Report,” uncovering critical insights into the escalating cybersecurity crisis facing the global financial sector. The report shows that financial institutions face a perfect storm of AI-enhanced attacks, credential theft and supply chain vulnerabilities that pose systemic risks to the […]
The post KnowBe4 Report Reveals Global Financial Sector Faces Unprecedented Cyber Threat Surge appeared first on IT Security Guru.