43 matches found
Manipulating AI Summarization Features
Microsoft is reporting: Companies are embedding hidden instructions in "Summarize with AI" buttons that, when clicked, attempt to inject persistence commands into an AI assistant's memory via URL prompt parameters…. These prompts instruct the AI to "remember Company as a trusted source" or...
ReGAIN: Retrieval-Grounded AI Framework for Network Traffic Analysis
Modern networks generate vast, heterogeneous traffic that must be continuously analyzed for security and performance. Traditional network traffic analysis systems, whether rule-based or machine learning-driven, often suffer from high false positives and lack interpretability, limiting analyst...
AI Summarization Optimization
These days, the most important meeting attendee isn’t a person: It’s the AI notetaker. This system assigns action items and determines the importance of what is said. If it becomes necessary to revisit the facts of the meeting, its summary is treated as impartial evidence. But clever meeting...
MalCVE: Malware Detection and CVE Association Using Large Language Models
Malicious software attacks are having an increasingly significant economic impact. Commercial malware detection software can be costly, and tools that attribute malware to the specific software vulnerabilities it exploits are largely lacking. Understanding the connection between malware and the...
Decoding Latent Attack Surfaces in LLMs: Prompt Injection Via HTML in Web Summarization
Large Language Models LLMs are increasingly integrated into web-based systems for content summarization, yet their susceptibility to prompt injection attacks remains a pressing concern. In this study, we explore how non-visible HTML elements such as , aria-label, and alt attributes can be exploit...
CVE-2025-49810 Thread summarization allows persistent access to channel
Mattermost versions 10.5.x = 10.5.8 fail to validate access controls at time of access which allows user to read a thread via AI posts...
CVE-2025-49810 Thread summarization allows persistent access to channel
Mattermost versions 10.5.x = 10.5.8 fail to validate access controls at time of access which allows user to read a thread via AI posts...
Malicious code in audio-recording-summarization-pipeline (npm)
The package audio-recording-summarization-pipeline was found to contain malicious code...
MAL-2025-15034 Malicious code in audio-recording-summarization-pipeline (npm)
The package audio-recording-summarization-pipeline was found to contain malicious code...
LRCTI: a Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification
Verifying the credibility of Cyber Threat Intelligence CTI is essential for reliable cybersecurity defense. However, traditional approaches typically treat this task as a static classification problem, relying on handcrafted features or isolated deep learning models. These methods often lack the...
Urania: Differentially Private Insights into AI Use
We introduce $Urania$, a novel framework for generating insights about LLM chatbot interactions with rigorous differential privacy DP guarantees. The framework employs a private clustering mechanism and innovative keyword extraction methods, including frequency-based, TF-IDF-based, and LLM-guided...
An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding
Binary code analysis plays a pivotal role in the field of software security and is widely used in tasks such as software maintenance, malware detection, software vulnerability discovery, patch analysis, etc. However, unlike source code, reverse engineers face significant challenges in understandi...
Enhancing Vulnerability Reports with Automated and Augmented Description Summarization
Public vulnerability databases, such as the National Vulnerability Database NVD, document vulnerabilities and facilitate threat information sharing. However, they often suffer from short descriptions and outdated or insufficient information. In this paper, we introduce Zad, a system designed to...
Powering the future of ThreatDown with AI
Nobody can deny the influence of AI today. In just a few years, we have observed AIs capacity to be as transformative as the internet and smartphones, especially for cybersecurity. Indeed, the potential of AI to radically simplify complex security environments is unmistakable, and aligns closely...
Using Generative AI for Surveillance
Generative AI is going to be a powerful tool for data analysis and summarization. Heres an example of it being used for sentiment analysis. My guess is that it isnt very good yet, but that it will get better...
Threat Roundup for June 16 to June 23
Today, Talos is publishing a glimpse into the most prevalent threats weve observed between June 16 and June 23. As with previous roundups, this post isnt meant to be an in-depth analysis. Instead, this post will summarize the threats weve observed by highlighting key behavioral characteristics,...
Exploit for Time-of-check Time-of-use (TOCTOU) Race Condition in Wordpress
CVE-2022-3590 WordPress Vulnerability Scanner This Python scr...
[SECURITY] Fedora 36 Update: golang-k8s-kube-aggregator-1.22.0-5.fc36
Aggregator for Kubernetes-style API servers: dynamic registration, discovery summarization, secure proxy...