Seeing AI Clearly: Building Visibility Across Modern AI Applications

AI applications span models, agents, and cloud environments in ways traditional security tools weren’t designed to understand. Here’s why visibility breaks — and how a new, implementation-agnostic approach helps teams safely adopt AI...

SafePickle: Robust and Generic ML Detection of Malicious Pickle-Based ML Models

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution RCE risks during model loading. Recent defenses, such as PickleBall, rely on per-library policy synthesis that requires comple...

A Systematic Literature Review on LLM Defenses against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy

The rapid advancement and widespread adoption of generative artificial intelligence GenAI and large language models LLMs has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs...

SynRAG: A Large Language Model Framework for Executable Query Generation in Heterogeneous SIEM System

Security Information and Event Management SIEM systems are essential for large enterprises to monitor their IT infrastructure by ingesting and analyzing millions of logs and events daily. Security Operations Center SOC analysts are tasked with monitoring and analyzing this vast data to identify...

[SECURITY] Fedora 42 Update: docker-buildkit-0.26.3-1.fc42

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

[SECURITY] Fedora 43 Update: docker-buildkit-0.26.3-1.fc43

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

[SECURITY] Fedora 42 Update: moby-engine-29.1.3-1.fc42

Docker is an open source project to build, ship and run any application as a lightweight container. Docker containers are both hardware-agnostic and platform-agnostic. This means they can run anywhere, from your laptop to the largest EC2 compute instance a nd everything in between =E2=80=94 and...

UIXPOSE: Mobile Malware Detection Via Intention-Behaviour Discrepancy Analysis

We introduce UIXPOSE, a source-code-agnostic framework that operates on both compiled and open-source apps. This framework applies Intention Behaviour Alignment IBA to mobile malware analysis, aligning UI-inferred intent with runtime semantics. Previous work either infers intent statically, e.g.,...

Behavior-Aware and Generalizable Defense against Black-Box Adversarial Attacks for ML-Based IDS

Machine learning based intrusion detection systems are increasingly targeted by black box adversarial attacks, where attackers craft evasive inputs using indirect feedback such as binary outputs or behavioral signals like response time and resource usage. While several defenses have been proposed...

[SECURITY] Fedora 41 Update: docker-buildkit-0.26.1-1.fc41

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

[SECURITY] Fedora 42 Update: docker-buildkit-0.26.1-1.fc42

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

[SECURITY] Fedora 43 Update: docker-buildkit-0.26.1-1.fc43

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

A Single-Root, Multi-Curve, Context-Isolated, PQC-Pluggable Cryptographic Identity Primitive with Stateless Secret Rotation

Cryptographic identity anchors modern decentralized systems, yet current standards like BIP-39 and BIP-32 are structurally insufficient for the demands of multi-curve, multi-domain, and post-quantum PQC environments. These legacy schemes rely on a monolithic identity root with no inherent context...

[SECURITY] Fedora 43 Update: docker-buildkit-0.25.2-1.fc43

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

[SECURITY] Fedora 41 Update: docker-buildkit-0.25.2-1.fc41

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

[SECURITY] Fedora 42 Update: docker-buildkit-0.25.2-1.fc42

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

QueryIPI: Query-Agnostic Indirect Prompt Injection on Coding Agents

Modern coding agents integrated into IDEs combine powerful tools and system-level actions, exposing a high-stakes attack surface. Existing Indirect Prompt Injection IPI studies focus mainly on query-specific behaviors, leading to unstable attacks with lower success rates. We identify a more sever...

[SECURITY] Fedora 43 Update: docker-buildkit-0.25.0-1.fc43

Concurrent, cache-efficient, and Dockerfile-agnostic builder toolkit...

SecureLearn - an Attack-Agnostic Defense for Multiclass Machine Learning against Data Poisoning Attacks

Data poisoning attacks are a potential threat to machine learning ML models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned with particular ML algorithms. Furthermore, most defenses a...

Everyone Needs AIR: An Agnostic Incident Reporting Framework for Cybersecurity in Operational Technology

Operational technology OT networks are increasingly coupled with information technology IT, expanding the attack surface and complicating incident response. Although OT standards emphasise incident reporting and evidence preservation, they do not specify what data to capture during an incident,...