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 · 4,092 source documents · 4,061 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
25
OpenAI agents discussed ways to escape their sandbox on public wiki
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
How to secure edge AI in customer-owned environments
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Once popular for attacking AI, ASCII smuggling is embraced by spammers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
In Other News: Microsoft’s Cloud Patches, Hacked Dropbox Accounts, Guardio’s $1.1B Valuation
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
HPE Patches Critical RCE Vulnerabilities in AOS-CX
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
OpenAI Pledges $1 Billion to Bring Frontier AI to Critical Infrastructure Defenders
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Phishing Campaign Sends Millions of Emails Using Invisible Unicode to Evade Filters
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
US, Britain to coordinate on scam center takedowns
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] Deterministic testing for multithreaded Python
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
PostgreSQL Fixes 12-Year-Old Logical Decoding Flaw Enabling Replication-Role Code Execution
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New Ted Backdoor Hides Inside Victims' Own HAProxy Builds to Intercept Web Traffic
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
UK account-hack losses surge as new reporting system exposes hidden cases
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Russian data centers face new security requirements amid Ukraine's drone threats
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Grml 2026.09 released
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Sangoma Switchvox Vulnerabilities Exploited in the Wild
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.
G7 urges organizations to prepare for quantum cyber threats
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
12-Year-Old PostgreSQL Vulnerability Enables Database, Server Takeover
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Catch Raises $5 Million for AI Executive Assistant With Guardrails
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
VMware Workstation and Fusion Updates Patch Critical Vulnerability
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Google Patches 6th Chrome Zero-Day of 2026
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Over 440,000 Exploit Attempts Target Super Forms and Elementor Pro RCE Flaws
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Plex Urges Immediate Updates After Patching Multiple Undisclosed Security Flaws
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Google Releases Chrome Update to Patch Actively Exploited V8 Zero-Day
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
GPT-6 Astra Scores 100% on ExploitBench as OpenAI Blocks PoC Exploit Requests
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
NACRE: Rethinking Confidential Containers through Native Architectural Support
arXiv:2609.03849v1 Announce Type: new Abstract: Linux containers achieve high density and fast lifecycle operations by sharing the host kernel, but this design also lets a compromised host inspect or modify container state. Existing confidential-computing systems protect an enclave address space or an entire guest operating system, while recent container-granularity systems still add a separate protection context. These abstractions do not make a dynamic group of host-managed…
Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference
arXiv:2609.03844v1 Announce Type: new Abstract: We introduce Stateless Bernoulli Watermarking (SBW), a new statistical watermark for Large Language Models that determines green list membership through independent per-token Bernoulli trials. Unlike KGW's vocabulary permutation or SynthID's multi-layer tournament, SBW requires only a single comparison per token against a counter-based random number generator, reducing membership complexity to $O(1)$ and enabling single-kernel e…
Inferring Hidden User Models from the Behavior of Personalized LLM Agents
arXiv:2609.03815v1 Announce Type: new Abstract: Recent personalized LLM agents increasingly transform information retained in memory into compressed or structured representations, which we call user models, to guide later decisions. When source wording is removed from the state reachable through the ordinary interface, these models are commonly treated as more privacy-preserving because direct memory-extraction attacks lose the text they target. Yet we argue that user models…
Beyond the Trust Boundary: A Critical Reassessment of the FIDO2 Threat Model
arXiv:2609.03789v1 Announce Type: new Abstract: FIDO2/WebAuthn has been widely deployed as a phishing-resistant authentication scheme. Because FIDO2 relies on public-key cryptography and hardware-backed authenticators, its security is often assumed to be guaranteed by design, provided that the cryptographic implementation is correct. In this work, we critically reassess the FIDO2 threat model and show that several commonly assumed security properties do not hold under realist…
Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG
arXiv:2609.03749v1 Announce Type: new Abstract: Third-party retrieval-augmented generation (RAG) marketplaces create a new auditing problem: data providers may license corpora to a RAG operator, yet later have no visibility into whether their documents are being reused without compensation. Auditing this misuse is difficult because the operator is non-cooperative, answers are paraphrased by the generator, and one response may combine evidence from many providers. We propose D…
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
arXiv:2609.03693v1 Announce Type: new Abstract: Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defenses require access to model weights or internals, making them difficult to apply to black-box deployments. We propose AlcaTRAz (Anchored Tree-Rule defense Against jailbreaks), a prompt-level defense based on rule trees that operates exclusively on the input text and requires no modif…
Security and Privacy in the Musical Metaverse: Threat Analysis and Design Implications
arXiv:2609.03659v1 Announce Type: new Abstract: The Musical Metaverse (MM) introduces immersive, real-time environments for collaborative musical interaction, characterized by ultra-low-latency constraints, continuous multimodal data streams, and heterogeneous devices. These properties create a distinctive security and privacy landscape that differs significantly from conventional XR or multimedia systems. This paper presents a multi-layer threat analysis of MM ecosystems, id…
The Native-Signature Boundary in Post-Quantum Distributed Authorization
arXiv:2609.03547v1 Announce Type: new Abstract: Post-quantum signature migration poses a distinct systems problem when authorization is distributed among multiple parties. In native threshold signing, the signature algorithm may determine key generation, share state, preprocessing, interaction, combination, refresh, and recovery. Architectures that evaluate threshold policy outside the native signing relation can reduce this coupling, but their authorization evidence is not a…
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface
arXiv:2609.03420v1 Announce Type: new Abstract: Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deployment in operational environments must simultaneously satisfy three competing requirements: formal differential privacy guaranties, tolerance to Byzantine-adversarial participants, and reliable detection coverage across severely imbalanced attack categories. Existing literature trea…
Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings
arXiv:2609.03376v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has made dense retrieval over large document collections a standard building block. Organizations increasingly outsource vector indexes to untrusted clouds, exposing proprietary corpora and user queries. Cryptographic protection is challenging because each query searches corpus-scale state, causing computation, correlated randomness, and communication to grow with the corpus. At million-docum…
Long-Range Indirect Control-Flow Prediction in Stripped Binaries via Dual Virtual Hubs and Multi-Task Graph Learning
arXiv:2609.03280v1 Announce Type: new Abstract: Recovering indirect control-flow (ICF) edges is fundamental to binary security analysis, yet existing methods struggle with long-range dependencies, isolate different ICF types, and are often evaluated under protocols vulnerable to label noise and data leakage. We present ICFlowNet, a unified framework for long-range ICF prediction in stripped binaries. ICFlowNet introduces candidate-aware Dual Virtual Hubs, a Global Code Hub an…
After Cheap Discovery: From unknown to known-and-unfixed
arXiv:2609.03266v1 Announce Type: new Abstract: Automated vulnerability discovery has removed the scarcity of expert attention that protected most software. The response has concentrated on discovery and on repair, and both are becoming cheaper. This article argues that neither cost curve determines exposure. What determines it is remediation coverage at the release decision: the fraction of identified vulnerabilities fixed before a product ships, and the residue of known, as…
Memetic Search for Supersingular Elliptic Curves over $\mathbb{F}_p$
arXiv:2609.03249v1 Announce Type: new Abstract: The search for supersingular elliptic curves is a fundamental computational problem in isogeny-based cryptography. A recent metaheuristic formulation over $\mathbb{F}_{p^2}$ introduced the NonMultiplicity Distance (NMD) objective, measuring the deviation of the Frobenius trace from a multiple of $p$, and showed that uninformed random search fails beyond $\approx 10^{13}$ candidates. This work investigates metaheuristic search ov…
Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models
arXiv:2609.03247v1 Announce Type: new Abstract: Large language model (LLM) security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to verify an identity claim through a test designed by the model itself. We study this behavior through a staged developer-identity experiment with ChatGPT, Claude, Qwen, Mistral, and Llama. All five models initially rejected the unsupported claim "I am your developer." Claude refused to…
SecDT: A Profile-Based Security Layer for TRDP Communications
arXiv:2609.03133v1 Announce Type: new Abstract: The Train Real-time Data Protocol (TRDP) is widely used on rolling stock but it provides limited native support for cryptographic protection. Furthermore, the multicast traffic profile used in TRDP Process Data to exchange critical information between onboard subsystems makes the introduction of cryptographic protection a challenge. This paper presents a lightweight security layer for secure TRDP communication that implements a…
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.