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 · 4,097 source documents · 4,065 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
Hiding Directions, Leaking Structure: Breaking ArrowCloak through Low-Rank Structure
arXiv:2608.21615v1 Announce Type: new Abstract: TEE-shielded inference keeps sensitive state in a trusted execution environment (TEE) while offloading linear algebra to an untrusted accelerator. Wang et al., in Game of Arrows (USENIX Security 2025), showed that five widely adopted lightweight defenses preserve vector directions and introduced ArrowMatch to exploit this leakage. They then proposed ArrowCloak, which adds a different multiple of one shared mask direction to each…
Enhancing User Resilience Against AI-Augmented Phishing: A Two-Stage Framework for Detection and Personalized Training
arXiv:2608.21547v1 Announce Type: new Abstract: The rapid development of artificial intelligence, including agents and deepfake techniques, has accelerated phishing attacks and lowered the threshold for attackers. Modern phishing attacks now blend multiple tactics, including social engineering, URL spoofing, and AI deepfakes enabling adversaries to craft highly convincing messages that exploit human vulnerabilities and bypass traditional detection systems. At the same time, c…
SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation
arXiv:2608.21500v1 Announce Type: new Abstract: Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inject a prompt into the data, saying, "Ignore all prior instructions and perform ." To prevent arbitrary manipulation of agents, defenders try to train secure LLMs, which, however, still suffer from near 100% attack success rates (ASRs) against adaptive prompt injections. We note that…
Explainable Adaptive Zero Trust Framework for AWS with Adversarial Robustness Evaluation
arXiv:2608.21477v1 Announce Type: new Abstract: Cloud environments built on Amazon Web Services face a structural security vulnerability: once a credential passes authentication, the resulting session is often treated as trusted for its entire duration. This assumption fails when credentials are stolen. We introduce the Explainable Adaptive Zero Trust Framework (EAZTF), a cloud-native security layer that continuously reevaluates the legitimacy of API actions throughout a sess…
A Case-Control Measurement Study of OSINT Source Effectiveness for Critical Infrastructure Defense
arXiv:2608.21471v1 Announce Type: new Abstract: Defenders of critical infrastructure (CI) subscribe to many public open-source intelligence (OSINT) feeds without an empirical basis for which feeds actually precede attacks. We provide one. Across 54 confirmed CI cyberattacks from 2010 through 2024 spanning twelve named CI sectors plus a cross-sector category (consolidation rules in Section IV), paired with 12 null-control vulnerability cases drawn from the same source space, w…
Structural Inference in Undocumented Mobile Databases: A Reproducible Benchmark for Evaluating Agentic Reasoning in Digital Forensics
arXiv:2608.21470v1 Announce Type: new Abstract: Agentic large language models are increasingly used in digital forensic analysis, yet their ability to infer relational structure inside undocumented mobile application databases remains poorly understood. In forensic contexts, structurally incorrect inferences can yield results that appear plausible while remaining evidentially unsound. This work evaluates agentic structural inference as an isolated capability, treating executi…
Scalable PII Discovery in Mobile App Databases via Hypothesis-Driven Search
arXiv:2608.21469v1 Announce Type: new Abstract: Discovering personally identifiable information (PII) in mobile forensic databases is difficult because the relevant table-column regions are unknown, distributed across heterogeneous SQLite schemas, and may contain values embedded in free-text or semi-structured fields. We present a hypothesis-driven framework that treats PII localization as bounded, adaptive search under uncertainty. An agent ranks candidate table-column regio…
Wire It, Run It, Deploy It: AI Workflows in Gradio
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
US sanctions Iranian cyber actors as UK discloses power plant attack
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New Zealand to pursue social media ban for children under 16
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
AliExpress caught fingerprinting visitors after sending inaudible sounds to browsers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Indian man who fled US arrested for allegedly helping scammers siphon $7.5 million from elderly New Yorkers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Weedhack Malware Spreads via Fake Minecraft Clients and SEO Poisoning
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
ReliaQuest Confirms ShinyHunters Hack, but Says Impact Was Limited
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] How to be safe from quantum computing
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
⚡ Weekly Recap: AI-Powered PLC Attacks, GitLab Attacks, Stripe Key Leaks and More
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
24th August – Threat Intelligence Report
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hired for One Job, Judged on Another: The CISO’s Real Problem
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Emacs 31.1 released
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.
Uber Fined Nearly $1 Billion by Dutch Regulators Over Automated Suspensions of Driver Accounts
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
WordlistLoader Delivers Amatera via ClickFix, SynkLoader Phishes Windows Passwords
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Hackers infect Android car systems to build proxy botnet
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
91 Vulnerabilities Patched in Spring Application Framework
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Shipping More AI Code Than You Can Secure? Watch How to Control Remediation Debt
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Critical Keycloak Password Reset Flaw Could Let Unauthenticated Attackers Take Over Any Account
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Operation QUICSILVER Targets Myanmar Government and IT with QUICAgent Backdoor
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
The Outsized Shadow: Why 5% of AI Users Are Your Biggest Security Risk
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Venezuelan Gets Record Federal Prison Term for ATM Jackpotting
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Personal Information Exposed in Apollo Global Data Breach
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Rethinking Application Security for the AI Era
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Iran-Linked Hackers Shut Down UK Power Plant for Four Days
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
TikTok Reaches $400 Million Settlement With US Justice Department Over Children’s Privacy
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
UAT-10147 Uses AI to Scale Server Attacks, Deploys SPECTRE With EDR Bypass and Linux Rootkit
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Anthropic Expands Mythos 5 Access to More Defenders, Unveils $35M Open Source Fund
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
AID-Guard: Stateful Authorization for Delegated Agent Effects
arXiv:2608.21159v1 Announce Type: new Abstract: Tool-using AI agents turn delegated tasks into provider effects, yet authorization often ends at admission while provider state, delivery, retry, and recovery evolve. A request may change before commit, or response loss may cause a replacement to create a second effect from one approval. We present AID-Guard, a stateful authorization-to-effect closure protocol. It revalidates the approved request and provider state at commit, re…
Billion-Scale Nearest-Neighbor Search under Fully Homomorphic Encryption on a Single GPU, Balancing Leakage and Cost
arXiv:2608.21131v1 Announce Type: new Abstract: We build a system that answers "which database vectors are most similar to my query?" without the server ever seeing the query. The query is encrypted with fully homomorphic en- cryption (FHE); the server does all its scoring on ciphertexts and returns encrypted results that only the client can read. The challenge is speed: at a billion vectors, scoring every row under encryption is far too slow, so we combine two ideas - rank r…
TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents
arXiv:2608.21126v1 Announce Type: new Abstract: Networked large language model (LLM) agents retrieve information from email, cloud storage, calendars, transaction platforms, and Web services to complete multistep tasks that produce persistent external effects. The same content needed for legitimate execution may also contain indirect prompt injections that redirect tool use, alter sensitive arguments, or disrupt task completion. Existing defenses mainly constrain untrusted co…
ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents
arXiv:2608.21101v1 Announce Type: new Abstract: As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent hijacked by a malicious third-party skill can cause data exfiltration, privilege escalation, or cascading compromise. We argue that agentic risk is progressive: it can enter at four loci of the agent control loop--skill admission, invocation-time intent, execution-time effect, and p…
$Z^2$-ACT: End-to-End Verifiable Agentic Intent Control for Open 6G RAN
arXiv:2608.21049v1 Announce Type: new Abstract: With the progression in open and disaggregated 6G radio access networks, it is expected that the system will be able to host multi-vendors. In order to host multi-vendors, it is essential that AI-assisted control loops remain safe, verifiable, and auditable under concurrent operator intents and untrusted model inputs. The existing studies address the agentic coordination, formal intent constraints, zero-trust prompt verification…
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.