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
23
TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG
TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG arXiv:2607.20437v1 Announce Type: cross Abstract: Production Retrieval Augmented Generation (RAG) systems rely on aggregating multiple external documents to answer complex queries. However, the retrieved documents introduce a new threat surface that can be exploited to launch split-knowledge attacks. In this attack, the adversary injects documents that are individually benign but create false assoc…
Where You Tap Matters: A Probe-and-Model Benchmark for Open-Set RF Fingerprinting
Where You Tap Matters: A Probe-and-Model Benchmark for Open-Set RF Fingerprinting arXiv:2607.21564v1 Announce Type: new Abstract: Radio Frequency Fingerprint Identification (RFFI) enables transmitter identification at the physical layer by learning device-specific impairments from received signals, yet the literature is inconsistent about where in the receiver chain those samples should be collected. Since distinct transformations are applied to the signal by the different r…
Themis Consensus Extension v1: MEV Mitigation by Randomized Delayed Execution and Intent-Hiding Transactions in Application-Specific Blockchains
Themis Consensus Extension v1: MEV Mitigation by Randomized Delayed Execution and Intent-Hiding Transactions in Application-Specific Blockchains arXiv:2607.21406v1 Announce Type: new Abstract: Maximal extractable value (MEV) arises when privileged participants select, exclude, insert, or reorder pending transactions for private gain. We specify and analyze the Themis Consensus Extension v1, first published by Mangata in 2021. The design separates value extraction by reorderi…
Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation
Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation arXiv:2607.21325v1 Announce Type: new Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight. Existing authentication and authorization mechanisms establish identity and delegate authority, but do not inherently provide cryptographic …
Which Model Is Actually Serving You? IRIS: Budgeted Black-Box Auditing of Model Substitution and Routing Dilution in LLM Gateways
Which Model Is Actually Serving You? IRIS: Budgeted Black-Box Auditing of Model Substitution and Routing Dilution in LLM Gateways arXiv:2607.20860v1 Announce Type: new Abstract: Commercial LLM gateways mediate access to hosted models, but the served backend may not match the advertised one: it may substitute a cheaper model on every request or route only a fraction $\epsilon$ of requests to it. Prior black-box auditors often need a privileged signal (log-probabilities, token…
Classical Acceptance Is Not Hybrid Authentication: Measuring X.509 Verifier Semantics in Post-Quantum Migration
Classical Acceptance Is Not Hybrid Authentication: Measuring X.509 Verifier Semantics in Post-Quantum Migration arXiv:2607.20800v1 Announce Type: new Abstract: A relying party validating a hybrid X.509 certificate --- carrying both a classical and a post-quantum credential --- must distinguish whether its accepting judgment rests on the post-quantum evidence or only on the classical path. To preserve compatibility, the separable designs place that evidence where classical pa…
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests
IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests arXiv:2607.20759v1 Announce Type: new Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools. Coding agents inherit security risks from both the LLM backbone, where adversarial prompts, poisoned training data, and backdoor triggers can cause models to …
GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning
GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning arXiv:2607.20730v1 Announce Type: new Abstract: Large language models increasingly use search tools to retrieve up-to-date information, introducing a new attack surface in which retrieved documents can be manipulated. This risk is amplified by the development of generative engine optimization, which can make selected content more likely to be retrieved, cited, and adopted…
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing arXiv:2607.20723v1 Announce Type: new Abstract: This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs. LeakyLMs introduce…
Security Vulnerability Patterns in AI-Generated Code: A Cross-Model Comparative Study
Security Vulnerability Patterns in AI-Generated Code: A Cross-Model Comparative Study arXiv:2607.20713v1 Announce Type: new Abstract: LLM-based coding tools enable non-expert users to generate routine automation scripts that may enter enterprise workflows without meaningful security review. This study examines that risk directly. Code was collected from ChatGPT, Microsoft Copilot, and Google Gemini using identical prompts across three automation domains. Claude Code performe…
Evaluating Large Language Models for Symbolic Security Protocol Analysis
Evaluating Large Language Models for Symbolic Security Protocol Analysis arXiv:2607.20712v1 Announce Type: new Abstract: Security protocol verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether Large Language Models (LLMs) can perform comparable analysis. We test GPT and DeepSeek in chat and reasoning modes over three runs on 130 obfuscated AnB/AnBx protocols covering 388 security goals, scored against ProVerif and OFMC. Chat models reach…
Buzz to Boom: Detecting Message Progression Vulnerabilities in Electron Applications via Segmented Directed Fuzzing
Buzz to Boom: Detecting Message Progression Vulnerabilities in Electron Applications via Segmented Directed Fuzzing arXiv:2607.20698v1 Announce Type: new Abstract: Electron is a popular framework for building cross-platform desktop applications using web technologies. Such applications consist of multiple processes with different privilege levels that communicate via message passing. When inter-process messages carry attacker-controlled inputs, they can propagate across proc…
Enhancing Attack Detection Capabilities in BACnet/IP Networks Using Machine-Learning Models
Enhancing Attack Detection Capabilities in BACnet/IP Networks Using Machine-Learning Models arXiv:2607.20686v1 Announce Type: new Abstract: Building Automation Systems (BAS) manage critical building functions using protocols such as BACnet/IP, yet defenders have limited tooling and few labeled datasets for detecting BACnet-specific attacks. This work addresses these gaps through three contributions. First, CISA's Zeek BACnet parser is modified to produce a unified per-packet…
Geometric Configurations of Perturbed Jailbreak Prompts
Geometric Configurations of Perturbed Jailbreak Prompts arXiv:2607.20581v1 Announce Type: new Abstract: Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety. In this paper, we investigate the internal representations of such string-level perturbed jailbreak inputs in the small weight models of the Qwen-2.5-1.5B/-3B/-7B-Instruct and Llama-3.2-1B/-3B/-3.1-8B-Instruct …
Deepfake News Detection: A Multimodal Framework Integrating LipNet, DeepSpeech and ResNET for Enhanced Audio-Visual Analysis
Deepfake News Detection: A Multimodal Framework Integrating LipNet, DeepSpeech and ResNET for Enhanced Audio-Visual Analysis arXiv:2607.20579v1 Announce Type: new Abstract: Deepfake news refers to AI-generated (or AI ma-nipulated) multimedia content intentionally generated to deceive audiences by manipulating the facial expressions, or speech while maintaining the realistic appearance. The rapid progress of generative AI has made the synthesis of highly realistic fake videos…
AuthProbe: Specification-Driven, Multi-Identity Detection of Broken Object-Level Authorization in Recruitment API
AuthProbe: Specification-Driven, Multi-Identity Detection of Broken Object-Level Authorization in Recruitment API arXiv:2607.20574v1 Announce Type: new Abstract: Broken Object-Level Authorization (BOLA), also known as Insecure Direct Object Reference (IDOR), has topped the OWASP API Security ranking since 2019 and is the root cause of some of the largest exposures of applicant data in recruitment technology. The defining feature of this flaw class is that a malicious request…
PhantomSeal: Proactive Deepfakes Defense with Identity/Context Protection and Forensic Tracing
PhantomSeal: Proactive Deepfakes Defense with Identity/Context Protection and Forensic Tracing arXiv:2607.20564v1 Announce Type: new Abstract: Deepfakes, especially face-swapping attacks, pose significant challenges to authenticity, security, and ethics across science, engineering, and society. While most existing detection/tracing approaches operate post hoc, proactive defenses that aim to intervene before deepfake generation remain limited in terms of real-world effectiven…
The Signs Were There: What the First Autonomous Ransomware Case Confirms
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Mourning Dan Williams
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Russian Espionage Group Exploited Zimbra Zero-Day to Steal Mail and 2FA Codes
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Don’t swing at everything
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
International alert spotlights Russia-linked attacks on Zimbra webmail
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
State Department imposes visa restrictions on foreign cyber scammers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
OpenAI Fixes ChatGPT Agent Flaw That Could Let Attackers Forge an AI Insider
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
ThreatsDay: Android Spyware, PLC Attacks, AI Image Prompt Injection + 12 More Stories
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Is Patching Dead? Vulnerability Management in the Post-Mythos Era
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Email threat landscape: Q2 2026 trends and insights
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Chick-fil-A Accounts Get Fried in Credential Stuffing Attack
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] An operations structure for swap devices
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Russian Global Webmail Espionage
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Abstract Raises $25 Million to Expand Composable Security Operations Platform
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Claude Cowork Flaw Could Let AI Agent Escape Its VM and Access Mac Files
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Codeberg: Protecting our FLOSS commons from LLMs
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Major Australian energy supplier confirms customer data compromised
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Chaos Ransomware Uses msaRAT to Route C2 Traffic Through Headless Chrome and Edge
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Security updates for Thursday
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
China-Nexus JadeProx Uses New TriBack Loader in Government and Healthcare Attacks
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
What FATF’s 7th Crypto Compliance Report Card Means: Enforcement Must Catch Up With Legislation
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
How Synthetic Identity Fraud is Coming for Machine Identities
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.