Today's cyber intelligence queue

Two Compromised joyfill npm Packages Run RAT When Imported Into Node.js

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Stadium Summer: The Snyk Connect Fan Zone Tour

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

E-MagDiP: Electro-Magnetic based Differential Privacy for EEG based Community Sensing

E-MagDiP: Electro-Magnetic based Differential Privacy for EEG based Community Sensing arXiv:2607.25968v1 Announce Type: new Abstract: EEG-based community sensing programs are emerging globally as a tool to leverage aggregated brain data to gain insights into attentiveness of students and employees. But these programs raise privacy concerns because EEG signals contain sensitive personal information. Differential Privacy (DP) can protect individuals while preserving aggregate …

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs arXiv:2607.25936v1 Announce Type: new Abstract: LLMs are increasingly deployed in real-world applications, making inference efficiency and service reliability critical concerns due to their substantial computational costs. However, the autoregressive generation mechanism of LLMs enables malicious prompts to manipulate generation behaviors, inducing excessive token genera…

Stemma: Induced Decision Regions Reveal LLM Provenance

Stemma: Induced Decision Regions Reveal LLM Provenance arXiv:2607.25880v1 Announce Type: new Abstract: LLM provenance testing asks whether a suspect LLM belongs to the same lineage as a source. Existing black-box methods largely infer this relationship from response-level characteristics, but these characteristics may shift under adaptation or deployment even when the underlying meaning remains unchanged, weakening the reliability of provenance evidence. To address this limi…

A Structuration Approach to Theorizing Cybersecurity Practice: The STARC Model

A Structuration Approach to Theorizing Cybersecurity Practice: The STARC Model arXiv:2607.25734v1 Announce Type: new Abstract: The problem: Cybersecurity practice runs simultaneously across analysts, teams, organizations, sectors, and regulators, co-evolves with adversaries, and increasingly blends human and algorithmic decision-making. The theories applied to it operate at single organizational levels and cannot explain why organizations with broadly similar controls differ…

SignDeepSC: A Semantic Signature-based Approach for Robust Semantic Communication

SignDeepSC: A Semantic Signature-based Approach for Robust Semantic Communication arXiv:2607.25676v1 Announce Type: new Abstract: Semantic communication systems such as deep semantic communication (DeepSC) offer high efficiency but are vulnerable to adversarial attacks on their underlying neural networks. We address a physical-layer man-in-the-middle (MitM) threat in which an adversary injects perturbations into the transmitted signal to distort its meaning. We propose SignD…

Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion

Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion arXiv:2607.25572v1 Announce Type: new Abstract: We present a reproducible pipeline for mapping Common Vulnerabilities and Exposures (CVEs) to MITRE ATT&CK Enterprise techniques from free-text vulnerability descriptions. Rather than relying on the CWE->CAPEC->ATT&CK derivation chain, whose table-expansion artifacts we quantify, we train a multi-label classifie…

Optimistic Verifiable Claims: A Blockchain Protocol for Conditionally Confidential Bidding in Decentralized Manufacturing

Optimistic Verifiable Claims: A Blockchain Protocol for Conditionally Confidential Bidding in Decentralized Manufacturing arXiv:2607.25517v1 Announce Type: new Abstract: Decentralized manufacturing faces a pre-contractual impasse: a Provider cannot price a service accurately without inspecting the design file, yet the Consumer cannot share that file without exposing intellectual property. We introduce the Optimistic Verifiable Claim (OVC), a blockchain protocol that lets a C…

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering arXiv:2607.25479v1 Announce Type: new Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computation graphs are distributed by third parties and reused across downstream services. This reuse model creates a security-critical trust boundary: VLM deployments…

From Profiling to Parameterization: Physics-Guided Acoustic Eavesdropping via Smartphone Accelerometers

From Profiling to Parameterization: Physics-Guided Acoustic Eavesdropping via Smartphone Accelerometers arXiv:2607.25461v1 Announce Type: new Abstract: We present LEAKFORGE, a device-agnostic framework that converts cross-device accelerometer eavesdropping into a physics-guided data-generation problem. Crucially, device-specific leakage is not arbitrary; its dominant variation lies within a constrained family of audio-to-accelerometer transfer functions. LEAKFORGE samples th…

SafeStats: Efficient 2PC Protocols for Data Statistic-Related Functions

SafeStats: Efficient 2PC Protocols for Data Statistic-Related Functions arXiv:2607.25430v1 Announce Type: new Abstract: Statistical analysis on sensitive datasets like medical records and financial transactions is essential for decision-making, but raises significant privacy concerns. While existing secure Two-Party Computation (2PC) makes extensive efforts in designing the common secure primitives (e.g., addition and multiplication) or machine learning-related functions, fe…

Hybrid Analysis for Secure MCP Tool Use in LLM Agents

Hybrid Analysis for Secure MCP Tool Use in LLM Agents arXiv:2607.25297v1 Announce Type: new Abstract: The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactions between LLM agents and external environments, Model Context Protocol (MCP) tools have emerged as a de facto standard and have been widely integrated into these systems. However, the use of MCP tools also introduces new safet…

Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks

Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks arXiv:2607.25227v1 Announce Type: new Abstract: Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks:…

SecDrift: Measuring Sector-Conditioned Security Drift in AI-Generated Code

SecDrift: Measuring Sector-Conditioned Security Drift in AI-Generated Code arXiv:2607.25225v1 Announce Type: new Abstract: LLMs are increasingly used for code generation in critical infrastructure, yet the security effect of domain-specific prompting is understudied. We present SecDrift, a benchmark measuring sector-conditioned security drift: the change in static-analysis vulnerability rates when prompts are conditioned on industry contexts versus neutral baselines. We eval…

How to Watermark the RLWE Homomorphic Ciphertexts

How to Watermark the RLWE Homomorphic Ciphertexts arXiv:2607.25222v1 Announce Type: new Abstract: In recent years, homomorphic encryption (HE) schemes based on the Ring Learning with Errors (RLWE) problem have rapidly developed and been widely applied to secure computation tasks, including privacy-preserving deep learning inference, privacy-preserving database queries, and related applications. However, most existing HE schemes focus primarily on the feasibility and efficien…

MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics

MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics arXiv:2607.25107v1 Announce Type: new Abstract: Security and privacy are primordial requirements for Federated Learning (FL), especially in fields such as healthcare and genomics where sensitive information has to be analyzed. Our FL framework is designed to address these challenges while proposing a modular, flexible and micro-service architecture. More precisely, it integrates an eff…

An Attack on High Rate McEliece Cryptosystems Using Generalized Reed Solomon Codes with Weight $2$ Mask

An Attack on High Rate McEliece Cryptosystems Using Generalized Reed Solomon Codes with Weight $2$ Mask arXiv:2607.25027v1 Announce Type: new Abstract: Due to the insecurity of McEliece cryptosystems instantiated with Generalized Reed-Solomon codes, there have been several proposals of McEliece type systems that replace the permutation matrix by a matrix $M$ with larger row and column weight. In many of them, the secret key is still a GRS code. There have been successful att…

ZIMPAF & RedPhuzz: High-fidelity Web Application Fuzzing via Branch, Language Construct, and Function Call Monitoring

ZIMPAF & RedPhuzz: High-fidelity Web Application Fuzzing via Branch, Language Construct, and Function Call Monitoring arXiv:2607.25012v1 Announce Type: new Abstract: We present ZIMPAF, runtime interpreter instrumentation, and RedPhuzz, a fuzzer, to address key limitations of state-of-the-art fuzzers: inefficient instrumentation, the lack of knowledge of the execution environment, and limited web domain knowledge. ZIMPAF implements a novel multi-granular runtime interpreter i…

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments arXiv:2607.24964v1 Announce Type: new Abstract: Large language models are increasingly deployed for security-sensitive tasks such as vulnerability detection and code review. Their reliance on natural-language context embedded in source code exposes a previously underexplored attack surface: adversarial comments that can influence a detector's reasoning without changing program …

TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models

TYPO: Instruction-Dense Visual Jailbreaks against Commercial Closed-Source Image-Generation Models arXiv:2607.24897v1 Announce Type: new Abstract: Recent commercial image-generation models can generate high-quality images with readable text (e.g., posters, infographics, and manuals), attracting considerable attention. Yet we first show that this same capability also introduces a previously unreported safety vulnerability: these systems may refuse to generate harmful text dir…

Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations

Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations arXiv:2607.24896v1 Announce Type: new Abstract: Static malware detectors are commonly evaluated using clean-sample metrics such as accuracy, F1, ROC AUC, and PR AUC. However, these metrics provide limited insight into how learned malware representations behave when feature vectors are perturbed, how close samples move toward uncertain decision regions, or whether compressed representations…

Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study

Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study arXiv:2607.24893v1 Announce Type: new Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run. Per-step safety checks that judge each action in isolation may fail to recogni…

Trusting-Trust Attack against an Entire Linux Distribution through Binary Manipulation

Trusting-Trust Attack against an Entire Linux Distribution through Binary Manipulation arXiv:2607.24888v1 Announce Type: new Abstract: Ken Thompson's trusting-trust attack, in which a compromised compiler backdoors the programs it builds and reproduces the backdoor in subsequent rebuilds of itself, is widely regarded as a threat specific to compilers. We show that it is not. We construct a complete trusting-trust attack around GNU strip, an ordinary build utility that neithe…

The Missing Layer: Specification Infrastructure for AI Oversight

The Missing Layer: Specification Infrastructure for AI Oversight arXiv:2607.24866v1 Announce Type: new Abstract: AI safety has a missing layer. Interpretability, formal methods, security engineering, evaluation methodology, and reinforcement-learning safety each produce substantial work, but the resulting artifacts do not compose into deployable oversight: every team fielding an agentic system builds its own audit schema, policy dialect, monitoring stack, and escalation path…

The Mirage of LLM Guardrails: A Case Study in AI-Assisted Medical Note Manipulation

The Mirage of LLM Guardrails: A Case Study in AI-Assisted Medical Note Manipulation arXiv:2607.24859v1 Announce Type: new Abstract: The rapid deployment of large language models (LLMs) in healthcare settings makes the reliability of their built-in guardrails against malicious queries a question of urgent practical consequence. Yet the robustness of these mechanisms against deliberate misuse (in the healthcare context) remains poorly understood. In this paper, we investigate …

Multimodal User Authentication Method via Fusion of Keystroke Dynamics and Glove-Based Hand Kinematics

Multimodal User Authentication Method via Fusion of Keystroke Dynamics and Glove-Based Hand Kinematics arXiv:2607.24747v1 Announce Type: new Abstract: Although keystroke dynamics are cost-effective behavioral biometrics, their practical deployment is hindered by susceptibility to environmental variations. To address this, we propose a robust multimodal authentication framework that augments traditional keystroke dynamics using 19-dimensional hand kinematics. Features are cap…

VerusCoin - Rekt

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Tracking Over 35,000 Fake Sites in the 2026 World Cup Scam Wave

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Senate confirms Clayton as intel chief after delays

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

JFrog tries to spin OpenAI 0-day exploit of its app into a success story

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Claude AI Just Cracked a Post-Quantum Test Scheme and Found a Faster 7-Round AES Attack

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

[$] Progress toward compiling Linux with gccrs

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

The OlmoEarth Platform: Geospatial inference at planetary scale

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

LFM2.5-Encoders for Fast Long-Context Inference on CPU

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Tengu Botnet Reboots Compromised Linux Devices When Defenders Kill Its Process

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Cyera Acquiring Oasis Security in $1 Billion Deal

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

Wayfire 0.11 released

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.

India’s Bank of Baroda confirms cyber incident after hackers claim data theft

An evidence-built Forensia brief is ready now; publisher prose remains at the original source.