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 · 4,100 source documents · 4,068 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
28
Hijacked Hotel Wi-Fi Pushes Fake Updates to Deliver Surveillance Malware
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
CaptiveCrunch: Midnight Blizzard targets travelers worldwide for malware delivery and credential theft
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Likely illegally, Claude gained access to 3 networks. Will Anthropic be held to account?
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Suspected Chinese-Speaking Hackers Target Central Asian Governments With OctLurk and SilkLurk
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
CISA warns of spike in attacks on water systems as Minnesota incidents probed
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cyber Command plans Silicon Valley office to drive innovation
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Servo 0.4.0 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
HollowFrame Loader Deploys Matryoshka Backdoor in Spear-Phishing Attack on Law Firm
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
In Other News: OpenAI Open Source Tool, AWS Links Hacks to North Korea, Mythos Crypto Research
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cyberattacks on Minnesota Water Systems Investigated as Officials Warn About Iranian Hackers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Cheap Android TV Boxes Pose as Phones and Turn Owners’ Broadband Into Proxies
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
This month in security with Tony Anscombe – July 2026 edition
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
AI scammers outperform humans when it comes to building trust
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] The future of libraries in BPF
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Arch Linux disables AUR package adoption
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Security updates for Friday
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Three Recent Chrome Releases Fix 1,442 Flaws, More Than Prior 23 Updates Combined
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Anthropic says its AI hacked real-world companies in three incidents
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Researchers Report 84 Flaws in 4G and 5G Cores, Including a Session Hijacking Flaw
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
6 Reasons Why Device Code Phishing is the Fastest-Growing Threat of 2026
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Chinese Hacker Commands DeepSeek via Telegram to Launch Autonomous Attacks
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Google AI Uncovers 13-Year-Old Chrome Flaw Amid Record Patching Pace
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
The Xcode Assassin Returns: A Deep Dive Into the Latest XCSSET Version
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Critical Flaw Led to Azure Cosmos DB Pwnage
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
CareCloud Data Breach Impacts Over 350,000
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Critical Code Execution Vulnerability Patched in TeamCity
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Implementing Homomorphic Encryption-Based Logic Locking in System-on-Chip Designs
Implementing Homomorphic Encryption-Based Logic Locking in System-on-Chip Designs arXiv:2607.28542v1 Announce Type: new Abstract: This study presents a logic locking scheme based on the binary Ring Learning With Errors algorithm, implemented in a RISC-V System-on-Chip design. Unlike traditional logic locking methods that require providing users with raw locking parameters, the proposed approach secures critical logic paths in the privilege switching process without exposing …
Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation
Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation arXiv:2607.28226v1 Announce Type: new Abstract: World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedback into physical action. Rather than treati…
Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data
Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data arXiv:2607.28191v1 Announce Type: new Abstract: Federated learning enables multiple institutions to train shared models without exchanging raw clinical EEG data, but it does not fully prevent privacy leakage from individual model updates. This paper presents a privacy-preserving federated learning framework for clinical EEG data using masking-based secure aggregation as the core protection mech…
Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents
Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents arXiv:2607.28165v1 Announce Type: new Abstract: Large Language Model (LLM)-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction naturalness, it introduces a critical yet under-explored attack surface, as audio inputs inevitably contain environmental noise beyond user control.…
Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems
Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems arXiv:2607.28147v1 Announce Type: new Abstract: Autonomous multi-agent systems (AMAS) built on large language models (LLMs), such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively optimized over a comb…
Checking Information Flow in Cloud-based IoT Access Control Policies (Extended Version)
Checking Information Flow in Cloud-based IoT Access Control Policies (Extended Version) arXiv:2607.28088v1 Announce Type: new Abstract: Many cloud providers for IoT technologies offer access control mechanisms whose proper configuration is critical for security. However, verifying permissions in isolation is insufficient in a setting where devices have different levels of trust or are compartmentalised in various subsystems. This work analyses IoT access control policies to …
Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs
Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs arXiv:2607.28075v1 Announce Type: new Abstract: Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to an attacker-selected class. We study clean-label temporal poisoning, where a fixed timestamp transformation is applied only to the target-class training streams, leaving their labels unchanged. The transfor…
Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks arXiv:2607.27990v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) communicate through sparse binary spike events rather than dense activations, enabling energy-efficient inference on neuromorphic hardware and motivating their use in always-on, battery-powered edge systems. We show that this same efficiency advantage creates a distinct security risk: sponge attacks can increase inference…
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs arXiv:2607.27951v1 Announce Type: new Abstract: Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks: the same answer can help an authorized professional or an attacker, while an attacker can imitate a benign request and interaction history. We separate the capability released by the model from the evidence…
Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage
Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage arXiv:2607.27936v1 Announce Type: new Abstract: Existing backdoor attacks often become effective immediately after backdoor implantation and may therefore be exposed before exploitation. Machine unlearning activated dormant backdoors mitigate such behavioral exposure by remaining inactive after training and becoming effective only after selected tr…
Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components arXiv:2607.27886v1 Announce Type: new Abstract: Existing model inversion (MI) attacks predominantly rely on post-training optimization to recover private data from model outputs. However, these methods are fundamentally constrained by the target model's generalization bottleneck, often yielding generic features rather than specific identities, particularly on high-dimensional datase…
Adaptive Security at the Edge for 6G-Enabled Healthcare IoT
Adaptive Security at the Edge for 6G-Enabled Healthcare IoT arXiv:2607.27858v1 Announce Type: new Abstract: Healthcare IoT services increasingly rely on edge gateways to relay routine telemetry and deliver rare but timecritical alarms. Even short traffic bursts can inflate worstcase delay and interfere with urgent messages. We present NANOEDGEGUARD, a kernel-plane closed-loop controller that observes per-source traffic intensity at the edge and enforces an auditable, multi-t…
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.