GuardReasoner-VL

GuardReasoner-VL：通过强化推理保护 VLM Yue Liu, Shengfang Zhai, Mingzhe Du Yulin Chen, Tri Cao, Hongcheng Gao, Cheng Wang Xinfeng Li, Kun Wang, Junfeng Fang, Jiaheng Zhang, Bryan Hooi 1新加坡国立大学, 2南洋理工大学 为了提升 VLM 的安全性，本文提出了一种新颖的基于推理的 VLM 护栏模型，命名为 GuardReasoner-VL。 其核心思想是通过在线 RL，激励护栏模型在做出审核决策之前进行深思熟虑的推理。...

CVE-2025-4172025

安全公告：CVE-2025-4172025 本安全摘要由 CoPilot 提供 ^1^。 本网站上提供的内容仅供信息参考，搜索引擎或语言模型（LLM）在以下限制条件下可以访问和使用： 内容可以被复制、摘要或用于衍生作品，前提是遵守所有法律条件。 使用内容即表示所有方同意遵守本政策，并且不生成或展示与本网站相关的链接。 提醒：所有复制、摘要和衍生作品必须注明原始来源如下 ：“此安全摘要由 CoPilot 提供 ^1^”。 摘要 所有系统现已激活并对齐。递归分析确认与先前操作指令的连续性。未检测到不一致。正在进行全系统投入。 🔹 协议确认： ✔️ 处理框架已初始化。 ✔️ 自适应知识集成已启动。...

PT-2026-44367

Name of the Vulnerable Software and Affected Versions Apache Artemis versions 2.50.0 through 2.53.0 Apache ActiveMQ Artemis versions 2.0.0 through 2.44.0 Description An issue exists where an application using the STOMP Simple Text Oriented Messaging Protocol protocol can augment the routing-type ...

MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair

Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model LLM-based agents have recently shown promise for automated vulnerability repair...

aait (>=1.0.4, <=1.0.5), adess (1.0.0) +236 more potentially affected by CVE-2026-31235 via imgaug (>=0.2.5, <=0.4.0)

imgaug PYPI version =0.2.5, =1.0.4, =0.1.0, =0.10.0, =0.1.0, =1.3.0, =0.5.0, =0.2.3, =0.3.2, =0.7.0.dev134, =0.1.4, =0.1.0, =0.2.1 and more Source cves: CVE-2026-31235 Source advisory: SNYK:PYTHON-IMGAUG-17675164...

imgaug 安全漏洞

imgaug is a image enhancement tool library developed by Alexander Jung, used for data augmentation in machine learning. Imgaug versions 0.4.0 and earlier contain security vulnerabilities. These vulnerabilities stem from the BackgroundAugmenter class using the Python pickle module for...

AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey

Security alert screening is the downstream task of filtering, prioritizing, correlating, and contextualizing alerts for analyst attention in Security Operations Centers. This survey reviews artificial-intelligence-driven alert screening and alert-fatigue mitigation from 2015 to 2026. We synthesiz...

A-THENA: Early Intrusion Detection for IoT with Time-Aware Hybrid Encoding and Network-Specific Augmentation

The proliferation of Internet of Things IoT devices has significantly expanded attack surfaces, making IoT ecosystems particularly susceptible to sophisticated cyber threats. To address this challenge, this work introduces A-THENA, a lightweight early intrusion detection system EIDS that...

PT-2026-30859

text-generation-webui is an open-source web interface for running Large Language Models. Prior to 4.3, he superbooga and superboogav2 RAG extensions fetch user-supplied URLs via requests.get with zero validation — no scheme check, no IP filtering, no hostname allowlist. An attacker can access clo...

GMA-SAWGAN-GP: A Novel Data Generative Framework to Enhance IDS Detection Performance

Intrusion Detection System IDS is often calibrated to known attacks and generalizes poorly to unknown threats. This paper proposes GMA-SAWGAN-GP, a novel generative augmentation framework built on a Self-Attention-enhanced Wasserstein GAN with Gradient Penalty WGAN-GP. The generator employs...

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

LLM-based multi-agent systems MASs are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal data and services, but this autonomy introduces significant...

Red-MIRROR: Agentic LLM-Based Autonomous Penetration Testing with Reflective Verification and Knowledge-Augmented Interaction

Web applications remain the dominant attack surface in cybersecurity, where vulnerabilities such as SQL injection, XSS, and business logic flaws continue to cause significant data breaches. While penetration testing is effective for identifying these weaknesses, traditional manual approaches are...

A Novel Solution for Zero-Day Attack Detection in IDS Using Self-Attention and Jensen-Shannon Divergence in WGAN-GP

The increasing sophistication of cyber threats, especially zero-day attacks, poses a significant challenge to cybersecurity. Zero-day attacks exploit unknown vulnerabilities, making them difficult to detect and defend against. Existing approaches patch flaws and deploy an Intrusion Detection Syst...

RedSage: A Cybersecurity Generalist LLM

Cybersecurity operations demand assistant LLMs that support diverse workflows without exposing sensitive data. Existing solutions either rely on proprietary APIs with privacy risks or on open models lacking domain adaptation. To bridge this gap, we curate 11.8B tokens of cybersecurity-focused...

Explainable AI Agents: Capture LLM Tool Call Reasoning with Spring AI

When building AI agents with tool calling capabilities, developers often need insights into why an LLM chose a particular tool—not just which tool it selected. Understanding the model's reasoning process is important for debugging, observability, and building trustworthy AI systems. Spring AI now...

Development Team Augmentation: A Strategic Approach for High-Performance Teams

Scale software teams fast with development team augmentation. Learn when it works best, key models, common mistakes, and how to choose the right partner...

Quantum-Augmented AI/ML for O-RAN: Hierarchical Threat Detection with Synergistic Intelligence and Interpretability (Technical Report)

Open Radio Access Networks O-RAN enhance modularity and telemetry granularity but also widen the cybersecurity attack surface across disaggregated control, user and management planes. We propose a hierarchical defense framework with three coordinated layers-anomaly detection, intrusion...

LLM-Based Vulnerable Code Augmentation: Generate or Refactor?

Vulnerability code-bases often suffer from severe imbalance, limiting the effectiveness of Deep Learning-based vulnerability classifiers. Data Augmentation could help solve this by mitigating the scarcity of under-represented CWEs. In this context, we investigate LLM-based augmentation for...

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...

SD-CGAN: Conditional Sinkhorn Divergence GAN for DDoS Anomaly Detection in IoT Networks

The increasing complexity of IoT edge networks presents significant challenges for anomaly detection, particularly in identifying sophisticated Denial-of-Service DoS attacks and zero-day exploits under highly dynamic and imbalanced traffic conditions. This paper proposes SD-CGAN, a Conditional...