PINA: Prompt Injection Attack against Navigation Agents

Navigation agents powered by large language models LLMs convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide...

A Prompt-Based Framework for Loop Vulnerability Detection Using Local LLMs

Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources, or introduce logical errors that degrade performance and compromise security. The problem are often undetected by traditional static analyzers becau...

CVE-2025-55423

A command injection vulnerability exists in the upnp_relay() function of multiple ipTIME router models. The flaw occurs because the controlURL value, used to pass port-forwarding information to an upstream router, is passed to the system() function without proper validation or sanitization. An at...

CVE-2025-55423

A command injection vulnerability exists in the upnprelay function in multiple ipTIME router models because the controlURL value used to pass port-forwarding information to an upper router is passed to system without proper validation or sanitization, allowing OS command injection...

PT-2026-3636

Name of the Vulnerable Software and Affected Versions ipTIME routers A2003NS-MU versions 10.00.6 through 12.16.2 ipTIME routers N600 versions 10.00.8 through 12.16.2 ipTIME routers A604-V3 versions 10.01.6 through 10.07.2 ipTIME routers A6ns-M versions 10.01.6 through 14.19.4 ipTIME routers V508...

HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation

Large language models LLMs are being increasingly integrated into practical hardware and firmware development pipelines for code generation. Existing studies have primarily focused on evaluating the functional correctness of LLM-generated code, yet paid limited attention to its security issues...

Abusing the Internet of Medical Things: Evaluating Threat Models and Forensic Readiness for Multi-Vector Attacks on Connected Healthcare Devices

Individuals experiencing interpersonal violence IPV, who depend on medical devices, represent a uniquely vulnerable population as healthcare technologies become increasingly connected. Despite rapid growth in MedTech innovation and "health-at-home" ecosystems, the intersection of MedTech...

TrojanPraise: Jailbreak LLMs Via Benign Fine-Tuning

The demand of customized large language models LLMs has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with malicious data. Though this security issue has recently bee...

An Optimized Decision Tree-Based Framework for Explainable IoT Anomaly Detection

The increase in the number of Internet of Things IoT devices has tremendously increased the attack surface of cyber threats thus making a strong intrusion detection system IDS with a clear explanation of the process essential towards resource-constrained environments. Nevertheless, current IoT ID...

CVE-2026-0629

Authentication bypass in the password recovery feature of the local web interface across multiple VIGI camera models allows an attacker on the LAN to reset the admin password without verification by manipulating client-side state. Attackers can gain full administrative access to the device,...

CVE-2025-14233

Invalid free in CPCA file deletion processing on Small Office Multifunction Printers and Laser Printers which may allow an attacker on the network segment to trigger the affected product being unresponsive or to execute arbitrary code. : Satera LBP670C Series/Satera MF750C Series firmware v06.02...

CVE-2025-14234

Buffer overflow in CPCA list processing on Small Office Multifunction Printers and Laser Printers which may allow an attacker on the network segment to trigger the affected product being unresponsive or to execute arbitrary code. : Satera LBP670C Series/Satera MF750C Series firmware v06.02 and...

CVE-2025-14232

Buffer overflow in XML processing of XPS file in Small Office Multifunction Printers and Laser Printers which may allow an attacker on the network segment to trigger the affected product being unresponsive or to execute arbitrary code. : Satera LBP670C Series/Satera MF750C Series firmware v06.02...

Your 100 Billion Parameter Behemoth is a Liability

The "bigger is better" era of AI is hitting a wall. We are in an LLM bubble, characterized by ruinous inference costs and diminishing returns. The future belongs to Agentic AI powered by specialized Small Language Models SLMs. Think of it as a shift from hiring a single expensive genius to runnin...

PT-2026-3270

Name of the Vulnerable Software and Affected Versions TP-Link VIGI Cameras affected versions not specified Description An authentication bypass issue exists in the password recovery feature of the local web interface of TP-Link VIGI cameras. This allows an attacker on the Local Area Network LAN t...

Predicting Tail-Risk Escalation in IDS Alert Time Series

Network defenders face a steady stream of attacks, observed as raw Intrusion Detection System IDS alerts. The sheer volume of alerts demands prioritization, typically based on high-level risk classifications. This work expands the scope of risk measurement by examining alerts not only through the...

Canon’s various products have security vulnerabilities

Canon ImageRunner is a product of the Japanese company Canon. Canon ImageRunner is a series of all-in-one black-and-white printers. Canon imagePROGRAF is a large-format printer. Canon imageCLASS MF644Cdw is a smart and efficient 3-in-1 color multifunctional printer. Several Canon products have...

Canon’s various products have security vulnerabilities

Canon ImageRunner is a product of the Japanese company Canon. Canon ImageRunner is a series of all-in-one black-and-white printers. Canon Color imageCLASS is a series of printers. Canon Satera is also a series of printers. Several Canon products have security vulnerabilities; these vulnerabilitie...

Canon’s various products have security vulnerabilities

Canon ImageRunner is a product of the Japanese company Canon. Canon ImageRunner is a series of all-in-one black-and-white printers. Canon imagePROGRAF is a large-format printer. Canon imageCLASS MF644Cdw is a smart and efficient 3-in-1 color multifunctional printer. Several Canon products have...

CVE-2025-14237

Buffer overflow in XPS font parse processing on Small Office Multifunction Printers and Laser Printers which may allow an attacker on the network segment to trigger the affected product being unresponsive or to execute arbitrary code. : Satera LBP670C Series/Satera MF750C Series firmware v06.02 a...