Today's cyber intelligence queue

Anthropic’s Opus 5 Nears Mythos 5 on Finding Bugs, but Falls Short on Exploits

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

DentaQuest Data Breach Potentially Impacts Over 23 Million People

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

NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics

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

TELESHIM Abuses Telegram for C2 in Attacks Against Middle East Governments

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

GitHub Adds 3-Day Dependabot Cooldown to Limit Poisoned Package Adoption

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

MCBS Data Breach Affects 1.2 Million Individuals

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

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection

Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection arXiv:2607.21776v1 Announce Type: cross Abstract: Talking-face (TF) deepfake generation synthesizes photore- alistic facial video from a static source image and an au- dio signal, producing forgeries that current image-based detectors consistently fail to identify. Unlike face-swap ma- nipulation, TF synthesis has no underlying real video from which to inherit physiological characteristics, maki…

What AI Red-Team Evaluations Can and Cannot Prove

What AI Red-Team Evaluations Can and Cannot Prove arXiv:2607.21735v1 Announce Type: cross Abstract: Red-team evaluations of AI models support some claims and not others, and the boundary between the two is calculable rather than merely a matter of judgment. We define the evidential ceiling of an evaluation as the largest factor by which one result can move belief under a fixed testing budget, derive it in closed form for the benchmark null result, and use it to locate that b…

Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration arXiv:2607.21673v1 Announce Type: cross Abstract: Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized P\'olya urn, we prove almost-sure convergence to a mean-field equilibrium whose slope acts as a reproduction…

A Maximum Entropy Implementation of Differential Privacy Under Linear Invariants

A Maximum Entropy Implementation of Differential Privacy Under Linear Invariants arXiv:2607.22450v1 Announce Type: new Abstract: Differential privacy is the standard for ensuring data privacy and is widely used in major data publications, including reporting results from the U.S. decennial census. Common implementation of differential privacy uses independent Gaussian or Laplace noise addition to the database. However, there could be aggregate (linear) queries to the databas…

Kalyna Block Cipher: From Design Space Exploration to ASIC Design

Kalyna Block Cipher: From Design Space Exploration to ASIC Design arXiv:2607.22269v1 Announce Type: new Abstract: The Kalyna block cipher is a Ukrainian cryptography standard, selected through a national competition held between 2007 and 2010 and approved in 2015. Although its software implementations have been introduced, hardware-efficient implementations of the algorithm, i.e., accelerators, do not exist. In this paper, we explore various design architectures to implement…

trasgoDP: An Open Source Framework for Releasing Noised Tabular Microdata under Local Differential Privacy

trasgoDP: An Open Source Framework for Releasing Noised Tabular Microdata under Local Differential Privacy arXiv:2607.22230v1 Announce Type: new Abstract: trasgoDP is a modular, open-source, and easy-to-use Python framework for releasing tabular microdata under {\epsilon}-local differential privacy guarantees, as well as location data under geo-indistinguishability assumptions, designed to be installed and integrated within standard data science workflows. The software enabl…

DeFiScreener: Efficient DeFi Attack Pre-screening in Smart Contracts via Historical Case Matching

DeFiScreener: Efficient DeFi Attack Pre-screening in Smart Contracts via Historical Case Matching arXiv:2607.22184v1 Announce Type: new Abstract: Blockchain and its killer applications, particularly decentralized finance (DeFi), are gaining widespread adoption, with over 5,200 DeFi projects deployed on mainstream blockchains as of January 2026. At the same time, security risks in DeFi are becoming increasingly serious. However, existing DeFi detection tools usually cover onl…

Transforming Keystroke Noise to Text: Self-Supervised Acoustic Eavesdropping Attacks on Keyboards

Transforming Keystroke Noise to Text: Self-Supervised Acoustic Eavesdropping Attacks on Keyboards arXiv:2607.22094v1 Announce Type: new Abstract: We present a self-supervised acoustic eavesdropping attack that reconstructs typed text solely from keystroke sounds, without requiring labeled data for the target device. The proposed attack enables stealthy eavesdropping in two real-world scenarios-physical spaces (public and semi-public) and online meetings. Our method combines …

PoCEvolve: Generating Proof-of-Concept Exploits from Security Patches with Vulnerability-Aware Prompt Evolution

PoCEvolve: Generating Proof-of-Concept Exploits from Security Patches with Vulnerability-Aware Prompt Evolution arXiv:2607.22076v1 Announce Type: new Abstract: Ideally, the detailed information about a vulnerability should be made available together with the fixing commit. In practice, however, such details often become available only long after the commit, even when a CVE has already been published. During this window, the patch is already public, so attackers can reverse-e…

BioZKFHE: Scalable Encrypted Biometric Identification via Verifiable Homomorphic Similarity Evaluation

BioZKFHE: Scalable Encrypted Biometric Identification via Verifiable Homomorphic Similarity Evaluation arXiv:2607.22065v1 Announce Type: new Abstract: Large-scale biometric identification in outsourced settings requires two properties simultaneously: biometric templates and queries must remain protected during computation, and the encrypted similarity outputs produced by an untrusted compute node must be verifiably correct before any application result is released. Existing …

Agent Security Needs Redefinition through a Holistic Framework

Agent Security Needs Redefinition through a Holistic Framework arXiv:2607.22024v1 Announce Type: new Abstract: Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action. \textbf{We argue that agent security is fundamentally a contextual problem, and that the current content based framing systematically misdefines it.} A command to ``delete user d…

Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening

Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening arXiv:2607.22009v1 Announce Type: new Abstract: Microsoft's Active Directory (AD) is a directory service that enables the IT admin to manage security permissions and control access within a Windows domain network. As a core management system in many of organisation, AD has become a primary target for adversaries. While many solutions for hardening attack graphs exist, these efforts fall…

Ethereum NFT Smart Contracts: Knowledge-Guided Vulnerability Detection with LLM and Code Slicing

Ethereum NFT Smart Contracts: Knowledge-Guided Vulnerability Detection with LLM and Code Slicing arXiv:2607.21983v1 Announce Type: new Abstract: Ethereum non-fungible tokens (NFTs) implement ownership, transfer, authorization, and metadata operations through smart contracts, making contract vulnerabilities a direct risk to digital assets. Existing static analyzers provide efficient rule-based screening but can struggle with application-specific logic, whereas unconstrained l…

Incentives and Market Structure in Intent-Based Exchanges: Evidence from a Solver-Reward Reform

Incentives and Market Structure in Intent-Based Exchanges: Evidence from a Solver-Reward Reform arXiv:2607.21955v1 Announce Type: new Abstract: Intent-based decentralized exchanges delegate execution to a competitive class of agents -- solvers -- whose behavior is shaped by protocol-designed reward rules. We measure how a change to those rules reshapes who captures value, using a governance-dated natural experiment: CoW Protocol CIP-74 (effective 8 December 2025), which repl…

Cleaning the NTP Pool: Detecting and Mitigating NTP-Sourced IPv6 Scanning

Cleaning the NTP Pool: Detecting and Mitigating NTP-Sourced IPv6 Scanning arXiv:2607.21903v1 Announce Type: new Abstract: The ephemeral and random nature of IPv6 client addresses presents a practical challenge to attacks that depend on Internet-wide scanning or reconnaissance -- the adversary must first \emph{find} the client's IPv6 address. While a well-positioned passive adversary can potentially harvest some active IPv6 client addresses, such power is typically reserved f…

PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption

PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption arXiv:2607.21895v1 Announce Type: new Abstract: In the past decade, we have witnessed an exponential growth of deep learning models, platforms, and applications. While existing DL applications and Machine Learning as a service (MLaaS) frameworks assume fully trusted models, the need for privacy-preserving DNN evaluation arises. In a secure multi-party computation scenario, both…

Decentralized Compute on Untrusted Hardware Using Intel TDX and Encrypted CVMs

Decentralized Compute on Untrusted Hardware Using Intel TDX and Encrypted CVMs arXiv:2607.21865v1 Announce Type: new Abstract: The rapid growth of artificial intelligence workloads has generated an unprecedented demand for secure and scalable compute resources. However, centralized cloud providers continue to dominate both pricing and security models. In an increasingly competitive AI landscape, where the compromise of training data or model weights can confer a significant …

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification arXiv:2607.21839v1 Announce Type: new Abstract: Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data. This makes them especially attractive for auditing models deployed in sensitive domains such as healthcare or finance. For these protocols to be meaningf…

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

ToolGuardian: Declarative Security for AI Agent-Tool Interactions arXiv:2607.21835v1 Announce Type: new Abstract: LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy judgment into a single decision, or use heuristic/LLM enforcement th…

Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense

Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense arXiv:2607.21824v1 Announce Type: new Abstract: Agentic commerce platforms let AI agents autonomously discover services, move payments, and wield user credentials on their users' behalf, and they already handle real money. Their security has so far been studied almost entirely at the level of the AI model, through prompt injection and misalignment. We show that the…

Adversarial Prompts for Acceptance Collapse in Speculative Decoding

Adversarial Prompts for Acceptance Collapse in Speculative Decoding arXiv:2607.21804v1 Announce Type: new Abstract: Lossless acceleration schemes, such as speculative decoding, promise significant inference speedups by relying on dynamic token-level alignment between a draft and a target model. However, this guarantee of semantic equivalence masks a severe operational vulnerability: draft-target alignment can be systematically attacked. In this paper, we introduce ADSD, whic…

Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks

Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks arXiv:2607.21763v1 Announce Type: new Abstract: Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation study across 22 frontier models from 7 providers on 23 Cybench capture…

A method of Risk Analysis and threat management using analytic hierarchy process

A method of Risk Analysis and threat management using analytic hierarchy process arXiv:2607.21691v1 Announce Type: new Abstract: Efficient risk analysis and threat management are essential requirements of modern air defense (AD) systems. The paper is halfway between the analytic hierarchy process (AHP) and practical reasoning to model and analyze the risks and threats associated with military AD applications. The models are applied for decision-making tasks of AD command and…

StajChain: A Hyperledger Fabric-Based Multi-Party Internship Agreement System

StajChain: A Hyperledger Fabric-Based Multi-Party Internship Agreement System arXiv:2607.21643v1 Announce Type: new Abstract: Many administrative processes, such as internship agreement processes, often rely on manual approval workflows and centralized record-keeping. This makes the process susceptible to delays and unauthorized modification while introducing limited traceability. This study presents StajChain, a permissioned blockchain-based multi-party internship managemen…

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents arXiv:2607.21642v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing safeguards remain limited: generic guardrails do not model shel…

AFX Trade - Rekt

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

2607-secai

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

What Is AI Pentesting and How Does It Works?

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

Kernel prepatch 7.2-rc5

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

A Debian general resolution on LLM usage

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

Malvertising Sends Malware in Pieces, Then Makes the Browser Build the Executable

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

In remembrance of Dan Williams

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

Security updates for Saturday

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