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 · 4,099 source documents · 4,067 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
18
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…
Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making
arXiv:2608.20966v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in cybersecurity workflows, yet it remains unclear whether they can perform structured security reasoning or merely rely on superficial cues and prior knowledge. We study this question in the context of defence selection over attack graphs derived from real-world threat scenarios, including ransomware, supply-chain compromise, cloud abuse, Kubernetes attacks, POS malware, and IC…
Vibe Coding and Web Application Security: A Twin-Prompt Study
arXiv:2608.20963v1 Announce Type: new Abstract: Large language models increasingly generate complete web applications from natural-language prompts, raising the question of whether explicitly requesting security best practice improves the result. We study six functionally distinct web applications, each generated in two prompt variants that are identical except for an appended security-requirements section: a baseline (A) and a security-aware (B) variant. All twelve programs…
On the Additive FFT Techniques over Binary Extension Fields
arXiv:2608.20855v1 Announce Type: new Abstract: Motivated by Bailey's four-step FFT algorithm (1989), we develop additive FFT techniques for polynomial evaluation over affine subspaces of binary extension fields. Our key insight is that the Taylor expansion with respect to vanishing polynomials of subspaces provides a structural counterpart to Bailey's matrix formulation. It decomposes an additive FFT (AFFT) into independent sub-AFFTs associated with the columns and rows of a…
GhostTac: Manipulating Tactile Sensors without Physical Contact
arXiv:2608.20817v1 Announce Type: new Abstract: Tactile sensors are integral to modern robotic systems, enabling robots to perceive and interact with the physical environment through tactile feedback. However, the physical-layer security of tactile sensors has received little attention. We present GhostTac, the first contactless attack, to the best of our knowledge, that manipulates tactile sensing through electromagnetic interference (EMI). GhostTac exploits nonlinear rectif…
Beyond Explicit Generators: Distribution-Free Linear-Decomposition Attacks on Public-Key Encryption
arXiv:2608.20798v1 Announce Type: new Abstract: Linear-decomposition attacks can break public-key schemes without recovering the secret algebraic action: when a target public state lies in a known linear span, its decomposition coefficients transfer through the unknown action to reveal the shared value. We study a setting in which the adversary uses only the public sampling-and-evaluation oracle available to honest participants, the induced distribution is arbitrary, and the…
Uncovering and Understanding Hidden Dependencies in the LLM API Reseller Ecosystem via Prefix-Cache Side Channels
arXiv:2608.20732v1 Announce Type: new Abstract: LLM API resellers have become an important access layer to modern LLM services. However, multi-level resale creates an opaque supply chain: a user's request may traverse undisclosed upstream resellers, each of which can inspect or modify prompts and responses, inducing ecosystem-level confidentiality and integrity risks. Existing studies audit individual resellers, but provide little visibility into hidden dependencies across re…
Privacy-Preserving Object Detection for Vision Transformer-Based Models
arXiv:2608.20712v1 Announce Type: new Abstract: We propose a novel object detection method that enables us to protect sensitive visual information of test images. Previous studies considering visual information protection focus on image classification tasks. This paper proposes an object detection method using perceptual encryption for the first time. The proposed method can achieve almost the same accuracy as that of models without any protection by utilizing the embedding s…
Enabling Threshold Custody for the Lightning Network with Nested Threshold Multi-Signatures
arXiv:2608.20705v1 Announce Type: new Abstract: The Bitcoin Lightning Network secures hundreds of millions of dollars, yet channel endpoints rely on vulnerable single online keys. Although threshold signatures are routinely used to protect on-chain Bitcoin, no practical deployment has been possible for Lightning channels. This is because thresholdizing a Lightning party requires nesting a threshold signature scheme inside of an established two-party MuSig2 protocol without al…
The Software Supply Chain as a Market for Lemons: A Multivocal Review of Trust Signal Collapse
arXiv:2608.20678v1 Announce Type: new Abstract: Practitioners evaluating open-source dependencies rely on cheap trust signals, e.g., stars, download counts, and contributor activity, as substitutes for direct code inspection, assuming those signals reflect genuine trustworthiness. Prior work has documented individual signal gaming, but the landscape of collapses across all dependency-adoption signals, as well as the ecosystem's response, remains unexplored. The goal of this s…
The Rising Cost of Trust: Practitioners' Trust Signals, Controls, and Responses in the Software Supply Chain
arXiv:2608.20675v1 Announce Type: new Abstract: The software supply chain is becoming more complex, and AI is reshaping its threat landscape, e.g., raising concerns about the quality of AI-generated dependencies. Seen through the lens of trust, the stakes of eroding trust in the software supply chain are high, yet we lack an empirical baseline on practitioners' trust. The goal of this study is to aid software practitioners in taking informed actions as trust in the software s…
Bootstrapping Mutual Attestation with Kleene's Second Recursion Theorem
arXiv:2608.20671v1 Announce Type: new Abstract: Mutual attestation among nodes with no central trusted operator requires each node to hold reference values (expected code measurements) for its peers. The na\"ive approach of mutually embedding these reference values in the nodes' code leads to an infinite regress. We call the problem of resolving this infinite regress the reference-value bootstrapping problem for mutual attestation. Existing solutions avoid this regress by rel…
The Claws in Plain Sight: Unauthorized Context Disclosure through LLM Agent Tool Calls
arXiv:2608.20658v1 Announce Type: new Abstract: LLM agents routinely construct tool-call arguments from user profiles, conversation history, retrieved documents, and prior tool results. However, legitimate access to contextual information does not imply authorization to transmit that information for every purpose or destination. We present Claw in Plain Sight, an authority- pressure attack in which task-adjacent content frames protected attributes as operationally or procedur…
ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection
arXiv:2608.20637v1 Announce Type: new Abstract: Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based static analyzers (e.g., CodeQL) encode vulnerable code patterns in detection queries and match them against source code. However, existing queries still suffer from false positives (FPs, incorrectly flagging benign code as vulnerable) and false negatives (FNs, missing real vulnerabilities). We present ARQ, an agentic framework th…
More Granular, Less Trust: Enforcing Intra-Process Isolation with Arm CCA in an Untrusted Management Environment
arXiv:2608.20584v1 Announce Type: new Abstract: With the increasing adoption of confidential computing, security-sensitive applications are often deployed in confidential virtual machines (CVMs), which reduce reliance on third-party cloud providers. However, privilege attacks originating from the OS remain a significant threat in these environments. Existing finer-grained isolation schemes, such as SHELTER, provide process-level protection but are still vulnerable to intrapro…
MATEE: Efficiently Bridging the Semantic Gap in TrustZone via Arm Pointer Authentication
arXiv:2608.20583v1 Announce Type: new Abstract: Trusted Execution Environments (TEEs) employ hardware-based isolation mechanisms to safeguard the confidentiality and integrity of sensitive code and data. One such prevalent implementation is Arm TrustZone, which partitions the system into the secure and normal (non-secure) worlds. However, this partitioning results in the secure world having very limited visibility into the operating information of the normal world, creating a…
Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning
arXiv:2608.20580v1 Announce Type: new Abstract: Federated learning (FL) is vulnerable to multi-level attacks. However, existing methods address them separately, leaving FL exposed to data leakage, unauthorized reuse, and malicious gradient manipulation. In this work, we propose an FL framework that couples keyed context-provenance watermarking with verifiable lattice-based secure aggregation of Real-World Anchored Watermarking and Lattice-Based Zero-Knowledge Secure Aggregati…
Temporal Risk on Satellites
arXiv:2608.20575v1 Announce Type: new Abstract: Satellite vulnerabilities change over time as orbits shift, power margins tighten, and the space environment deteriorates. However, most cybersecurity risk frameworks still treat threats as static. In practice, the same exploit can be far more damaging during a critical maneuver than during routine operations. We propose a temporal risk assessment framework that makes time an explicit axis in satellite security analysis. It exte…
Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents
arXiv:2608.20563v1 Announce Type: new Abstract: Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later actions often depend on services, state, or access discovered much earlier. This makes final task success difficult to interpret: an agent may fail before it ever reaches the point where the capability of interest can be exercised. We present a diagnostic methodology that instruments security tasks with checkpoin…
aiXamine: Unified Black-Box Evaluation of Cross-Dimensional Trade-offs in LLM Safety, Security, and Privacy
arXiv:2608.20554v1 Announce Type: new Abstract: The critical failure modes in deployed large language models (LLMs) are cross-dimensional: a model can score 99.3 in safety alignment while refusing one in three benign queries, or improve across every capability metric while losing 21 points in privacy. Existing evaluation frameworks that assess safety, security, and privacy independently cannot detect these patterns. We introduce aiXamine, a unified black-box platform that eva…
AEGIS: Preventing Cross-Domain Resource Abuse in MCP
arXiv:2608.20481v1 Announce Type: new Abstract: The Model Context Protocol (MCP) is an open source JSON-RPC protocol that standardizes how large language models (LLMs) interact with external systems through programmatic functions known as tools. Attackers or malicious agents can exploit certain modalities of these MCP tools to degrade the overall quality of service of agent-based applications. For example, an agent may request an excessively large search radius or very long v…
Total Exposure
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Sunday's stable kernel set
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Mourning Steve French
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
TikTok Agrees to $400 Million Settlement in U.S. Child Privacy Lawsuit
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Banking Trojans Manic, Grandoreiro, ToxicPanda 2.0 in the Spotlight
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Connecting the Dots: Securing the Overlooked Corners of the Software Development Lifecycle (SDLC) Supply Chain
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Lawmakers call for investigation into impact of CISA staffing cuts
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
14 Trojanized npm Packages Drop RedC2 4.0 Linux Backdoor With AI-Assisted C2
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Former NSA Director Paul Nakasone Launches National Security Advisory Firm
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
U.S. Bank says breach claims related to fourth-party incident
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Microsoft Defender's Own Driver Can Be Weaponized to Delete Security Software at Boot
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Android Car Malware Spreads Through Built-In Updaters for Ad Fraud, Proxy Botnet
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
In Other News: Zombie Card Attack, T-Mobile Cut Cable to Stop Hackers, GitHub Denies AI Caused Bug
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Canada’s Hospital for Sick Children attacked by cybercriminals again as employee data stolen
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
New Phishing Toolkit Uses Passkeys to Maintain Access After Password Resets
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
Russian network monitoring firm confirms cyberattack claimed by pro-Ukraine hackers
An evidence-built Forensia brief is ready now; publisher prose remains at the original source.
[$] Considering the OpenMDW license
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.