Opening Forensia workspaceacquiring
Loading the current evidence view. Navigation and account controls remain available.
Loading recent evidenceacquiring
Intelligence reports
Loading the current evidence view. Navigation and account controls remain available.
Ordering reports and their extracted indicators.
Applying the current filters and ordering.
Forensia intelligence desk · 4,102 source documents · 4,070 stories
Live reporting, advisories and research arranged by editorial readiness. Thin sources stay visible, but they are clearly marked instead of being presented as complete analysis.
On this page
40 documents
Briefs ready now
40
Multi-source clusters
0
Publisher text withheld
31
SPARC: Automated Root-Cause Analysis of Pre-Silicon Power Side-Channel Leakage in the Processor Design Flow
SPARC: Automated Root-Cause Analysis of Pre-Silicon Power Side-Channel Leakage in the Processor Design Flow arXiv:2607.23218v1 Announce Type: new Abstract: Power-Side-Channel Leakage (PSCL) originates from architectural and micro-architectural artifacts in a processor and poses a severe threat to the confidentiality of cryptographic software. Consequently, pre-silicon PSCL evaluation is indispensable for secure hardware design. Existing frameworks are either limited by poor …
False Prophets: On the Security of World Models in Agentic Systems
False Prophets: On the Security of World Models in Agentic Systems arXiv:2607.23147v1 Announce Type: new Abstract: Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of these tasks requires the agent to predict the results of its actions. Recent research proposes to enhance predictive capabilities via specially trained environment simulators-world models. While world models can imp…
Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios
Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios arXiv:2607.23088v1 Announce Type: new Abstract: Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored. Existing benchmarks often rely on explicitly specified security requirements, failing to capture real-world scenarios where prompts are frequently ambiguous or incomplete. In this paper, we adop…
Traceable LLM Reasoning for Fake-Order Fraud Detection
Traceable LLM Reasoning for Fake-Order Fraud Detection arXiv:2607.23075v1 Announce Type: new Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability. To address these limitations, we propose DeepScrub, a reinforcement learning framework built upon large language models (LLMs) f…
GLST: Defending Confidence-Driven V2X Collaborative Perception Against Stealthy Multi-Attacker Feature Injection
GLST: Defending Confidence-Driven V2X Collaborative Perception Against Stealthy Multi-Attacker Feature Injection arXiv:2607.23059v1 Announce Type: new Abstract: Collaborative perception (CP) improves autonomous-driving perception by enabling connected vehicles to exchange intermediate features via V2X. Confidence-driven sparse communication reduces bandwidth by transmitting only perception-critical spatial regions, but creates a security risk: once a collaborator is compromi…
Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks
Mask2Shield: Strengthening LLM Safety against Neuron-Pruning Attacks arXiv:2607.23015v1 Announce Type: new Abstract: Large language models (LLMs) are safety-aligned before deployment to reduce harmful content generation. Yet neuron-level pruning attacks show that refusal can depend on a small set of removable units: disabling them can remove safety behavior while leaving much of the model usable. To address this problem, we introduce Mask2Shield (M2S), a masked-forward align…
Practical Post-Quantum Cryptography for Bandwidth Constrained or Non-Terrestrial Networks, and Power Constrained Devices
Practical Post-Quantum Cryptography for Bandwidth Constrained or Non-Terrestrial Networks, and Power Constrained Devices arXiv:2607.23007v1 Announce Type: new Abstract: Post-quantum (PQ) cryptographic algorithms, particularly for authentication, are more complex than classical algorithms and require larger certificates, signatures, and keys. Establishing a PQ-secure network connection increases bandwidth, memory, computation time, and energy consumption. These costs are espe…
A Modular Cyber Range Platform for Smart Energy Systems
A Modular Cyber Range Platform for Smart Energy Systems arXiv:2607.22943v1 Announce Type: new Abstract: Modern critical infrastructure requires realistic training tools that bridge the gap between digital vulnerabilities and physical consequences. This paper introduces a lightweight, modular Cyber Range (CR) designed to simulate Information Technology (IT) and Operational Technology (OT) environments with high fidelity. Using the FastAPI framework as backend and Quick Emulat…
ReCon: A Resource-Constrained Benchmark for LLM-Based Cybersecurity Compliance Across Ingestion and Retrieval Pipelines
ReCon: A Resource-Constrained Benchmark for LLM-Based Cybersecurity Compliance Across Ingestion and Retrieval Pipelines arXiv:2607.22885v1 Announce Type: new Abstract: With the increasingly aggressive cyber threat landscape for governments, businesses, and institutions, as information and/or cybersecurity implementations are increasingly under scrutiny by regulators, it has been pointed out that governance failure is one of the major reasons for a weakened cybersecurity post…
OFAC Sanctions Members of Hamas Financing Network
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
For Some, So-Called ‘Skynet Day’ Came too Close to Sci-Fi After a Rogue Agent Hacked Into a Startup
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Chaos in Teams vishing
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
The Generator Can't Be the Validator: What OpenAI's Hugging Face Incident Proves About AI Security
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Microsoft unveils AI security tools it says outperform competing platforms
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Outdated VPNs should be purged from federal agencies, senator says
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
NVIDIA Forms 37-Member Open Secure AI Alliance and Open-Sources NOOA Framework
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
UK court rejects Bahrain immunity claim in spyware case
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Health system in South Carolina, Georgia closes offices after malware affects networks
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Dysphoria IoT Botnet Adds Blockchain C2 and Victim Relays After JackSkid Disruption
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] Hazard pointers for the kernel
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Rethinking security for the age of AI
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Enhancing AI security through global AI red teaming
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
27th July – Threat Intelligence Report
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hackers used Telegram phishing campaign to target exiled Belarusian activist
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Activist charged with felony after giving border agent "duress code" that wiped his phone
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
GNU Binutils 2.47 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Public Exploit Released for Patched vBulletin Pre-Auth Code Execution Flaw
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New GitHub, PyPI Policies Boost Supply Chain Security
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
⚡ Weekly Recap: Rogue AI Agents, Check Point Exploit, Slopsquatting, ClickFix Lures and More
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
PTC Windchill Vulnerability Exploited in Ransomware Campaign
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Security updates for Monday
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
n8n Sandbox Escape Lets Workflow Editors Run OS Commands as the n8n Process
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
MedusaHVNC Malware Uses Hidden Windows Desktops to Evade Detection
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Operation BlueDash Deploys Level RMM and ScreenConnect via Fake Teams Update
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Nvidia and Tech Giants Launch AI Security Alliance
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hackers used autonomous AI agent to spy on Thailand's finance ministry
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Coca-Cola Confirms Data Breach After Fairlife Ransomware Attack
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Beelzebub Raises $3.4 Million for Hacker-Trapping Platform
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
What’s Hiding in Your Mobile Apps? Lookout MSEC Aims to Find Out
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cruciferra Crypter Uses BYOVD and Process Ghosting to Hide Windows Malware
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
story desk
clustered evidenceWatchGuard Patches Critical Vulnerabilities
developing · new
Microsoft Rolls Out 22 Fresh Security Patches
source only · new
Google Patches 6th Chrome Zero-Day of 2026
developing · new
Cisco Warns of Unpatched Secure Email Flaws, Patches Critical Switch Vulnerabilities
developing · new
Cisco Patches Critical Crosswork, Secure Workload Vulnerabilities
source only · new
filter by source
sharing classification
TLP describes sharing sensitivity, not copyright permission. Reader text is limited to source-provided descriptive material; original reporting stays with its publisher.