Today's cyber intelligence queue

Upbound Group Says Data Breach Led to $13 Million in Fraudulent Contract Losses

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

Chaos ransomware's msaRAT: Living off the browser to build a covert C2 channel

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

Preview: Cisco Talos at Black Hat USA 2026

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

Google Adds Selfie Video Recovery for Users Locked Out of Their Accounts

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

Assaf Keren Appointed New CISO of Meta

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

New Check Point Zero-Day Vulnerability Exploited in the Wild

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

Nine-Year-Old RefluXFS Linux Flaw Gives Local Users Root on Default RHEL Installs

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

Check Point Patches Exploited SmartConsole Flaw Allowing Full Admin Access

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

US Warns of Iranian Hackers Targeting Siemens, Schneider, and Rockwell ICS Devices

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

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents arXiv:2607.19837v1 Announce Type: cross Abstract: Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to extract: what they are, how they are used, and which agent weaknesses …

End-to-End Differential Privacy in Training Deep Neural Network Classifiers

End-to-End Differential Privacy in Training Deep Neural Network Classifiers arXiv:2607.19580v1 Announce Type: cross Abstract: Differentially private machine learning enables model training on sensitive data while ensuring that individual data is unlikely to be recoverable from the parameters of the resulting model. However, existing work often privatizes both training inputs and their labels, and these protections may be conservative when labels are public or can be safely m…

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents arXiv:2607.19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited. We introduce a lightweight black-box auditing framework that injects four silent failure profile…

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI

The Chronos Vulnerability: A Taxonomy of Temporal Persistence and Memory-Based Deception in Agentic AI arXiv:2607.19433v1 Announce Type: cross Abstract: The transition from stateless generative models in artificial intelligence to stateful, autonomous agents represents an architectural evolution that, while providing the capabilities of long-term planning and the automation of enterprise workflows, also represents the introduction of a new form of security threat, the Chrono…

Recovering Clinical Utility Under Differential Privacy: Empirical Validation of Adaptive Federated Aggregation on Heterogeneous Cardiovascular Datasets

Recovering Clinical Utility Under Differential Privacy: Empirical Validation of Adaptive Federated Aggregation on Heterogeneous Cardiovascular Datasets arXiv:2607.19403v1 Announce Type: cross Abstract: Validating federated learning frameworks on real clinical data is an essential step between proof-of-concept demonstrations in controlled synthetic environments and deployment in real multicenter healthcare settings. A prior architectural study by the same authors (Tertulino a…

Constant-time decoding of Gabidulin codes and their generalizations with application to RQC

Constant-time decoding of Gabidulin codes and their generalizations with application to RQC arXiv:2607.20305v1 Announce Type: new Abstract: Gabidulin codes are a rank metric analog of Reed-Solomon codes. Although these codes are used in different very efficient rank-based cryptosystems like the RQC cryptosystem or the Loidreau cryptosystem, there was no constant-time implementation of Gabidulin codes, when having a constant-time implementation is crucial for real-life develo…

Chained Attacks on Drone-Based Federated Learning: From Network Disruption to Device Impersonation

Chained Attacks on Drone-Based Federated Learning: From Network Disruption to Device Impersonation arXiv:2607.20280v1 Announce Type: new Abstract: Edge Intelligence (EI) has emerged as a transformative model for mission-critical unmanned platforms, such as drone swarms, by enabling collaborative model training at the network periphery. However, the security of FL deployments depends on both network availability and robust client authentication mechanisms. This paper investig…

The Ethics of Autonomous AI Agents for Offensive Security

The Ethics of Autonomous AI Agents for Offensive Security arXiv:2607.20255v1 Announce Type: new Abstract: LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling -- deterministic, narrowly scoped, and operated by trained practitioners -- agentic security tools exhibit \textit{indeterminacy} along three independent dimensions. First, their actions are drawn from a non-deterministic policy whose outputs resist both ex-ante …

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis

Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis arXiv:2607.20216v1 Announce Type: new Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language models (LLMs) demonstrate impressive capabilities for technical artifact interpretation, the opacity and escalating API costs of closed-weight frontier models…

Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection

Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection arXiv:2607.20003v1 Announce Type: new Abstract: An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices. But there is a trade-off between security and energy use, as strong detection models can drain the battery of devices fast. This work tests different Multi-Layer Perceptron (MLP) model configurations to balance malware d…

HijackKV: New Threat in Position-Independent KV Cache Reuse

HijackKV: New Threat in Position-Independent KV Cache Reuse arXiv:2607.19957v1 Announce Type: new Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs). Traditional prefix-based reuse has low cache hit rates across inference requests because it requires exact token and position matches. To improve efficiency, recent system optimizations introduce position-independent KV reuse, allowing KV cache to be reused whenever identical text chunks ap…

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning arXiv:2607.19894v1 Announce Type: new Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations. First, they focus on fine-tuning-based backdoors (e.g., PEFT modules) and fail to address insidious model-editing attacks that…

DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection

DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection arXiv:2607.19829v1 Announce Type: new Abstract: Most existing LLM safety evaluation and defense methods follow a static formulation: jailbreak vulnerabilities are evaluated with fixed attack methods, and guardrails are trained on fixed malicious prompt datasets. However, real-world adversaries continuously evolve their capabilities and expand the attack space. To address this challeng…

An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports

An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports arXiv:2607.19742v1 Announce Type: new Abstract: Cyber Threat Intelligence (CTI) reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for automated attack-path reasoning. Existing CTI extraction methods focus on indicators, entities, or TTP labels without modeling the execution conditions and resulting states of each at…

GhostPrompt: Cross-Image Adversarial Prompt for Vision-Language Models

GhostPrompt: Cross-Image Adversarial Prompt for Vision-Language Models arXiv:2607.19683v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are known to be vulnerable to adversarial attacks, where subtle perturbations to images or texts induce erroneous outputs. However, most text-based attacks are adapted from language-model-centric methods, in which the visual input is fixed during optimization, resulting in adversarial prompts that are tied to specific images and…

FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense

FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense arXiv:2607.19674v1 Announce Type: new Abstract: Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches that lack semantic understanding, making them vulnerable to stealthy triggers and harmful to benign structures. To solve this, we present FedLSG, the first framework that integrates large language models…

Twin Agent: Context Residual Compression for Privilege Separated Agents

Twin Agent: Context Residual Compression for Privilege Separated Agents arXiv:2607.19595v1 Announce Type: new Abstract: Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and careful control of information flow, but often degrade utilit…

Examining User Behavior and Cognitive Biases in Personal Password Security

Examining User Behavior and Cognitive Biases in Personal Password Security arXiv:2607.19586v1 Announce Type: new Abstract: Despite increasing awareness of cybersecurity risks, users continue to engage in insecure password practices, such as reusing passwords, choosing weak credentials, and neglecting security recommendations. The study explores the behavioral and cognitive factors that influence password decision-making by integrating insights from behavioral economics, part…

When HTTP 402 Meets the Blockchain: Risks on Emerging x402 Payments

When HTTP 402 Meets the Blockchain: Risks on Emerging x402 Payments arXiv:2607.19545v1 Announce Type: new Abstract: x402 is an emerging payment protocol for Web APIs and autonomous AI agents. x402 extends HTTP 402 with a payment negotiation flow and delegates payment proof verification and on-chain settlement to third-party facilitators. As a result, facilitators serve as a shared payment infrastructure for many independent merchants. This centralizes trust and validation in…

Integrity of peer-to-peer distributed LLM inference under malicious nodes

Integrity of peer-to-peer distributed LLM inference under malicious nodes arXiv:2607.19490v1 Announce Type: new Abstract: Peer-to-peer distributed inference executes a Large Language Model (LLM) on pooled consumer hardware by spreading its layers across many nodes. Every request passes through nodes that are owned and controlled by multiple independent parties. However, in this setting, any party can tamper with the output of its layers to corrupt the end result. Recomputing…

Intelligent Disruption: Undetectable Attacks on Wireless Autoencoders

Intelligent Disruption: Undetectable Attacks on Wireless Autoencoders arXiv:2607.19448v1 Announce Type: new Abstract: Adversarial attacks can degrade the legitimate decision performance in wireless autoencoder communications. However, in complex scenarios with multiple adversaries, the cumulative leakage interference (CLI) caused by the multiple parallel attacks increases the chance of detecting the attacks, while dynamical environments also make the fixed attack strategies …

Building Trust in Autonomous Commerce: A Verifiable Global Event Timeline and AI-Ready Fraud Intelligence Layer

Building Trust in Autonomous Commerce: A Verifiable Global Event Timeline and AI-Ready Fraud Intelligence Layer arXiv:2607.19436v1 Announce Type: new Abstract: Agentic commerce protocols such as AP2 and ACP define mechanisms for secure agent-initiated transactions but do not provide interoperable, tamper-evident auditability or verifiable temporal ordering of events across heterogeneous domains. This paper addresses these gaps by proposing a verifiable global event timeline …

ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems arXiv:2607.19432v1 Announce Type: new Abstract: The Model Context Protocol (MCP) is an open-source standard that allows AI agents to connect to external tools, databases, and services. While this connectivity enables powerful agent capabilities, it also introduces multi-step attacks that existing per-call defenses cannot reliably detect. Attackers can compose …

ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems arXiv:2607.19430v1 Announce Type: new Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions. Existing defenses guard only the input boundary (IBProtector, Llama Guard, perplexity filters, SmoothLLM) or run outside the application as opaque, stochastic p…

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models arXiv:2607.19424v1 Announce Type: new Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates. We propose JailMeter, an evidence-based evaluation framework designed to more faithfully measure jailbreak effectiveness. Inspired by the Info…

[$] LWN.net Weekly Edition for July 23, 2026

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

A Case for Critical Thinking

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

Federal Agencies Warn of Ongoing PLC Exploitation Against Critical U.S. Infrastructure

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

Inside the OpenAI – Hugging Face Incident: The AI Breach With No Human Attacker Behind It

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

13M+ Emails Sent in Tech Support Scam Targeting Users, Organizations in Japan

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