PT-2025-34152

Name of the Vulnerable Software and Affected Versions: Linksys RE6250 versions 1.0.013.001 through 1.2.07.001 Linksys RE6300 versions 1.0.013.001 through 1.2.07.001 Linksys RE6350 versions 1.0.013.001 through 1.2.07.001 Linksys RE6500 versions 1.0.013.001 through 1.2.07.001 Linksys RE7000 version...

WaFusion: a Wavelet-Enhanced Diffusion Framework for Face Morph Generation

Biometric face morphing poses a critical challenge to identity verification systems, undermining their security and robustness. To address this issue, we propose WaFusion, a novel framework combining wavelet decomposition and diffusion models to generate high-quality, realistic morphed face image...

From .pth to p0wned: Abuse of Pickle Files in AI Model Supply Chains

Executive summary Recent threat research highlights a growing risk in the Python and machine learning ML ecosystem: the exploitation of serialized model files, specifically those using Python’s pickle module. While commonly used for saving and loading ML models, pickle files can execute arbitrary...

From Semantic Web and MAS to Agentic AI: a Unified Narrative of the Web of Agents

The concept of the Web of Agents WoA, which transforms the static, document-centric Web into an environment of autonomous agents acting on users' behalf, has attracted growing interest as large language models LLMs become more capable. However, research in this area is still fragmented across...

Exploring User Security and Privacy Attitudes and Concerns toward the Use of General-Purpose LLM Chatbots for Mental Health

Individuals are increasingly relying on large language model LLM-enabled conversational agents for emotional support. While prior research has examined privacy and security issues in chatbots specifically designed for mental health purposes, these chatbots are overwhelmingly "rule-based" offering...

REAL-IoT: Characterizing GNN Intrusion Detection Robustness under Practical Adversarial Attack

Graph Neural Network GNN-based network intrusion detection systems NIDS are often evaluated on single datasets, limiting their ability to generalize under distribution drift. Furthermore, their adversarial robustness is typically assessed using synthetic perturbations that lack realism. This...

LB-LINK多款产品 访问控制错误漏洞

LB-LINK BL-AC1900 and others are products of China Bilink LB-LINK.LB-LINK BL-AC1900 is a wireless router.LB-LINK BL-AC3600 is a dual-band Gigabit wireless router that supports both 2.4GHz and 5GHz bands and is suitable for home and small office networks.LB-LINK AC2100AZ3 is a router. An access...

The Man behind the Sound: Demystifying Audio Private Attribute Profiling Via Multimodal Large Language Model Agents

Our research uncovers a novel privacy risk associated with multimodal large language models MLLMs: the ability to infer sensitive personal attributes from audio data -- a technique we term audio private attribute profiling. This capability poses a significant threat, as audio can be covertly...

PRM-Free Security Alignment of Large Models Via Red Teaming and Adversarial Training

Large Language Models LLMs have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies predominantly rely on Process Reward Models PRMs to evaluate...

From Alerts to Intelligence: a Novel LLM-Aided Framework for Host-Based Intrusion Detection

Host-based intrusion detection system HIDS is a key defense component to protect the organizations from advanced threats like Advanced Persistent Threats APT. By analyzing the fine-grained logs with approaches like data provenance, HIDS has shown successes in capturing sophisticated attack traces...

Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats

Protecting cyberspace requires not only advanced tools but also a shift in how we reason about threats, trust, and autonomy. Traditional cybersecurity methods rely on manual responses and brittle heuristics. To build proactive and intelligent defense systems, we need integrated theoretical...

AICrypto: a Comprehensive Benchmark for Evaluating Cryptography Capabilities of Large Language Models

Whitepaper called AICrypto: A Comprehensive Benchmark For Evaluating Cryptography Capabilities Of Large Language Models...

When Developer Aid Becomes Security Debt: a Systematic Analysis of Insecure Behaviors in LLM Coding Agents

LLM-based coding agents are rapidly being deployed in software development, yet their security implications remain poorly understood. These agents, while capable of accelerating software development, may inadvertently introduce insecure practices. We conducted the first systematic security...

Exploit for Improper Neutralization in Dlink Dns-320_Firmware

CVE-2024-10915 - D-Link NAS Command Injection Exploit This Py...

ARPaCCino: an Agentic-RAG for Policy As Code Compliance

Policy as Code PaC is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code IaC environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In th...

CVE-2025-53630

llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the ggufinitfromfileimpl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability is fixed in commit 26a48ad699d50b6268900062661bd22f3e792579...

The Prompt as a Rulebook - Guiding LLM Agents Beyond Basic Instructions

...

Phishing Detection in the Gen-AI Era: Quantized LLMs Vs Classical Models

Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency. This paper presents a comparative evaluation of traditional Machine Learning ML, Deep Learning DL, and quantized...

Can Large Language Models Improve Phishing Defense? A Large-Scale Controlled Experiment on Warning Dialogue Explanations

Phishing has become a prominent risk in modern cybersecurity, often used to bypass technological defences by exploiting predictable human behaviour. Warning dialogues are a standard mitigation measure, but the lack of explanatory clarity and static content limits their effectiveness. In this pape...

Securing the Frontier - Navigating Security in LLM-Integrated Systems

In the previous parts of this series, we've explored the exciting new ways Large Language Models LLMs can integrate with APIs and act as intelligent As we integrate LLMs deeper into our applications, the attack surface naturally expands...