ThinkTrap: Denial-Of-Service Attacks against Black-Box LLM Services Via Infinite Thinking

Large Language Models LLMs have become foundational components in a wide range of applications, including natural language understanding and generation, embodied intelligence, and scientific discovery. As their computational requirements continue to grow, these models are increasingly deployed as...

The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines

Cybersecurity has become one of the earliest adopters of agentic AI, as security operations centers increasingly rely on multi-step reasoning, tool-driven analysis, and rapid decision-making under pressure. While individual large language models can summarize alerts or interpret unstructured...

Towards Small Language Models for Security Query Generation in SOC Workflows

Analysts in Security Operations Centers routinely query massive telemetry streams using Kusto Query Language KQL. Writing correct KQL requires specialized expertise, and this dependency creates a bottleneck as security teams scale. This paper investigates whether Small Language Models SLMs can...

A Comprehensive Study of Supervised Machine Learning Models for Zero-Day Attack Detection: Analyzing Performance on Imbalanced Data

Among the various types of cyberattacks, identifying zero-day attacks is problematic because they are unknown to security systems as their pattern and characteristics do not match known blacklisted attacks. There are many Machine Learning ML models designed to analyze and detect network attacks,...

EUVD-2025-201545

A vulnerability was determined in Linksys RE6500, RE6250, RE6300, RE6350, RE7000 and RE9000 1.0.013.001/1.0.04.001/1.0.04.002/1.1.05.003/1.2.07.001. Affected by this issue is the function RE2000v2RepeatergetwirelessclientlistsetClientsName of the file modform.so. Executing manipulation of the...

CVE-2025-14133 Linksys RE6500/RE6250/RE6300/RE6350/RE7000/RE9000 mod_form.so AP_get_wireless_clientlist_setClientsName stack-based overflow

A vulnerability was found in Linksys RE6500, RE6250, RE6300, RE6350, RE7000 and RE9000 1.0.013.001/1.0.04.001/1.0.04.002/1.1.05.003/1.2.07.001. Affected by this vulnerability is the function APgetwirelessclientlistsetClientsName of the file modform.so. Performing manipulation of the argument...

CVE-2025-14133 Linksys RE6500/RE6250/RE6300/RE6350/RE7000/RE9000 mod_form.so AP_get_wireless_clientlist_setClientsName stack-based overflow

A vulnerability was found in Linksys RE6500, RE6250, RE6300, RE6350, RE7000 and RE9000 1.0.013.001/1.0.04.001/1.0.04.002/1.1.05.003/1.2.07.001. Affected by this vulnerability is the function APgetwirelessclientlistsetClientsName of the file modform.so. Performing manipulation of the argument...

Linksys多款产品 安全漏洞

Linksys RE6250, among others, is a wireless extender from Linksys, USA. A security vulnerability exists in various Linksys products, which stems from an incorrect manipulation of the parameter clientsname0 in the file modform.so, which could result in a stack buffer overflow. The following produc...

Linksys多款产品 安全漏洞

Linksys RE6250, among others, is a wireless extender from Linksys, USA. A security vulnerability exists in various Linksys products, which stems from an incorrect manipulation of the parameter clientsname0 in the file modform.so, which could result in a stack buffer overflow. The following produc...

TeleAI-Safety: A Comprehensive LLM Jailbreaking Benchmark Towards Attacks, Defenses, and Evaluations

While the deployment of large language models LLMs in high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited by an imbalanced...

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models

Large Language Models LLMs have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal domains. Most existing jailbreak methods revolve around Prompt...

Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification

Malicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and finance. While the research community has made significant progress in WebShell detection i.e., distinguishing malicious...

ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications

AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models LLMs. However, these systems introduce novel and evolving security challenges, includi...

EUVD-2025-201179

An issue was discovered on Thermo Fisher Ion Torrent OneTouch 2 INS1005527 devices. When they are powered on, an X11 display server is started. The display server listens on all network interfaces and is accessible over port 6000. The X11 access control list, by default, allows connections from...

CVE-2025-11787

Command injection vulnerability in the operating system in Circutor SGE-PLC1000/SGE-PLC50 v9.0.2 through the 'GetDNS', 'CheckPing' and 'TraceRoute' functions...

CISA, Australia, and Partners Author Joint Guidance on Securely Integrating Artificial Intelligence in Operational Technology

CISA and the Australian Signals Directorate’s Australian Cyber Security Centre, in collaboration with federal and international partners, have released new cybersecurity guidance: Principles for the Secure Integration of Artificial Intelligence in Operational Technology. This guidance aims to hel...

Chopping AI Down to Size: Turning Disruptive Technology into a Strategic Advantage

Most people know the story of Paul Bunyan. A giant lumberjack, a trusted axe, and a challenge from a machine that promised to outpace him. Paul doubled down on his old way of working, swung harder, and still lost by a quarter inch. His mistake was not losing the contest. His mistake was assuming...

Picklescan Bugs Allow Malicious PyTorch Models to Evade Scans and Execute Code

Three critical security flaws have been disclosed in an open-source utility called Picklescan that could allow malicious actors to execute arbitrary code by loading untrusted PyTorch models, effectively bypassing the tool's protections. Picklescan, developed and maintained by Matthieu Maitre...

Whispering poetry at AI can make it break its own rules

Most of the big AI makers don't like people using their models for unsavory activity. Ask one of the mainstream AI models how to make a bomb or create nerve gas and you'll get the standard "I don't help people do harmful things" response. That has spawned a cat-and-mouse game of people who try to...

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Whitepaper from researchers at MIT, Northeastern University, and Meta. For an LLM to correctly respond to an instruction it must understand both the semantics and the domain i.e., subject area of a given task-instruction pair. However, syntax can also convey implicit information Recent work shows...