LLM

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…

September 18, 2025
0 comment
Read More >>

LunaLock Ransomware threatens victims by feeding stolen data to AI models

LunaLock, a new ransomware gang, introduced a unique cyber extortion technique, threatening to turn stolen art into AI training data. A new ransomware group, named LunaLock, appeared in the threat landscape with a unique cyber extortion technique, threatening to turn stolen art into AI training data. Recently, the LunaLock group targeted the website Artists&Clients and […]

September 9, 2025
0 comment
Read More >>

AI in Government

Just a few months after Elon Musk’s retreat from his unofficial role leading the Department of Government Efficiency (DOGE), we have a clearer picture of his vision of government powered by artificial intelligence, and it has a lot more to do with consolidating power than benefitting the public. Even so, we must not lose sight of the fact that a different administration could wield the same technology to advance a more positive future for AI in government.

To most on the American left, the DOGE end game is a dystopic vision of a government run by machines that benefits an elite few at the expense of the people. It includes AI …

September 8, 2025
0 comment
Read More >>

Indirect Prompt Injection Attacks Against LLM Assistants

Really good research on practical attacks against LLM agents.

“Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous”

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…

September 3, 2025
0 comment
Read More >>

PromptLock: The First AI-Powered Ransomware & How It Works

Introduction AI-powered malware has become quite a trend now. We have always been discussing how threat actors could perform attacks by leveraging AI models, and here we have a PoC demonstrating exactly that. Although it has not yet been observed in active attacks, who knows if it isn’t already being weaponized by threat actors to […]

The post PromptLock: The First AI-Powered Ransomware & How It Works appeared first on Blogs on Information Technology, Network & Cybersecurity | Seqrite.

August 29, 2025
0 comment
Read More >>

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.

In a proof of concept video of the attack…

August 27, 2025
0 comment
Read More >>

Subverting AIOps Systems Through Poisoned Input Data

In this input integrity attack against an AI system, researchers were able to fool AIOps tools:

AIOps refers to the use of LLM-based agents to gather and analyze application telemetry, including system logs, performance metrics, traces, and alerts, to detect problems and then suggest or carry out corrective actions. The likes of Cisco have deployed AIops in a conversational interface that admins can use to prompt for information about system performance. Some AIOps tools can respond to such queries by automatically implementing fixes, or suggesting scripts that can address issues…

August 20, 2025
0 comment
Read More >>

LLM Coding Integrity Breach

Here’s an interesting story about a failure being introduced by LLM-written code. Specifically, the LLM was doing some code refactoring, and when it moved a chunk of code from one file to another it changed a “break” to a “continue.” That turned an error logging statement into an infinite loop, which crashed the system.

This is an integrity failure. Specifically, it’s a failure of processing integrity. And while we can think of particular patches that alleviate this exact failure, the larger problem is much harder to solve.

Davi Ottenheimer …

August 14, 2025
0 comment
Read More >>

Microsoft unveils Project Ire: AI that autonomously detects malware

Microsoft’s Project Ire uses AI to autonomously reverse engineer and classify software as malicious or benign. Microsoft announced Project Ire, an autonomous artificial intelligence (AI) system that can autonomously reverse engineer and classify software. Project Ire is an LLM-powered autonomous malware classification system that uses decompilers and other tools, reviews their output, and determines the […]

August 7, 2025
0 comment
Read More >>