Latest threat reports & articles

arxiv_cs_cr · tlp:amber · 6/29/2026, 4:00:00 AM

Exploring and Exploiting Synchrony Limitations of Time-Triggered Network-Agnostic Guardians arXiv:2606.27819v1 Announce Type: new Abstract: Time-triggered communication protocols rely on trusted components known as guardians to enforce adherence to predetermined network schedules. Network-agnostic guardians offer an efficient and scalable distributed solution with reduced implementation cost and complexity compared to network-aware alternatives. However, this efficiency is b…

arxiv_cs_cr · tlp:amber · 6/29/2026, 4:00:00 AM

Reliable Homomorphic Matching for Fuzzy Labeled PSI at Scale arXiv:2606.27803v1 Announce Type: new Abstract: Fuzzy Labeled Private Set Intersection (FLPSI) lets a receiver learn the labels of enrolled records similar to its query, and nothing else. Constructions based on a set-threshold reduction reach practical performance: a query matches a record when the two agree on a threshold number of components, and the private matching is delegated to an inner set-threshold kernel.…

arxiv_cs_cr · tlp:amber · 6/29/2026, 4:00:00 AM

AdvScan: Black-Box Adversarial Example Detection at Runtime through Power Analysis arXiv:2606.27704v1 Announce Type: new Abstract: TinyML models deployed on edge devices are increasingly adopted in safety/security-critical applications, making them a prime target for adversarial example (AE) attacks where inputs are modified to cause misclassifications. However, existing AE detection methods either require white-box model access, which is often unavailable in licensed black-…

arxiv_cs_cr · tlp:amber · 6/29/2026, 4:00:00 AM

On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models arXiv:2606.27567v1 Announce Type: new Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken. We prove this is not a coincidence: in shared-embedding architectures that lack enforced control-data separation, perfect prompt-injection prevention is mathematically impossible. We formalize prompted systems as Prompted …

arxiv_cs_cr · tlp:amber · 6/29/2026, 4:00:00 AM

When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems arXiv:2606.27511v1 Announce Type: new Abstract: Large Language Model (LLM)-based question-answering (QA) systems are increasingly deployed in sensitive domains such as healthcare, mental health counseling, and legal consultation. Federated learning (FL) enables collaborative training without sharing raw client data, for which locally trained models are aggregated at a central server (i.e., a cl…

arxiv_cs_cr · tlp:amber · 6/29/2026, 4:00:00 AM

Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks arXiv:2606.27701v1 Announce Type: cross Abstract: While voice control is rapidly becoming a ubiquitous vector of human-AI communication, the risks facing these systems remain poorly understood. This is, in part, a product of the difficulties in scaling strictly digital adversarial workflows to the physical world. These scale barriers have led the community to abstract away key acoustic factors relating t…

trend_micro · tlp:amber · 6/29/2026, 12:00:00 AM

TONResolver RAT Abuses TON Blockchain to Target Japan's Hotel Industry In this blog entry, TrendAI™ Research examines a wave of phishing emails observed in May 2026 that targeted Japanese accommodation facilities using Booking.com, detailing the victims, attack techniques used, and characteristics of the malware involved. TONResolver RAT Abuses TON Blockchain to Target Japan's Hotel Industry | Trend Micro (US) search close About Mission and Culture Mission and Culture A…

snyk_blog · tlp:amber · 6/29/2026, 12:00:00 AM

Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice? Snyk VulnBench JS 1.0: 300 repeated scans show LLM security findings vary by run, while SAST and models catch different vulnerability gaps. Snyk VulnBench JS 1.0: LLM Bug Repeatability | Snyk You need to enable JavaScript to run this app. Skip to main content Platform Resources Company Pricing Evo New EN Select your language English Deutsch Español Français 日本語 Português Login Free and Team Plan Customers Snyk app.sn…

lwn_kernel · tlp:amber · 6/28/2026, 8:08:00 PM

Kernel prepatch 7.2-rc1 The 7.2-rc1 kernel prepatch is out for testing. Linus said: " So two weeks have passed, and the merge window is closed. Things look reasonably normal for this release (knock wood). " Kernel prepatch 7.2-rc1 [LWN.net] LWN .net News from the source Content Weekly Edition Archives Search Kernel Security Events calendar Unread comments LWN FAQ Write for us User: Password: | | Log in / Subscribe / Register Kernel prepatch 7.2-rc1 [Posted June 28, 2026 by …

lwn_kernel · tlp:amber · 6/27/2026, 1:59:19 PM

Three stable kernel updates The 7.1.2 , 7.0.14 , and 6.18.37 stable kernel updates have been released; each contains a relatively small number of important fixes. Note that 7.0.14 is the end of the 7.0.x series. Three stable kernel updates [LWN.net] LWN .net News from the source Content Weekly Edition Archives Search Kernel Security Events calendar Unread comments LWN FAQ Write for us User: Password: | | Log in / Subscribe / Register Three stable kernel updates [Posted June…

lwn_kernel · tlp:amber · 6/26/2026, 6:01:46 PM

[$] Reports from OSPM 2026, day three The Power Management and Scheduling in the Linux Kernel Summit , which still goes by the historical acronym OSPM, was held in Cambridge, UK, in mid-April. As has become traditional, the presenters at that event have since written summaries of their sessions, and this work has kindly been made available to LWN for publication. The third day's sessions covered a wide range of topics, including GPU affinity, profile-guided scheduling, parav…

lwn_kernel · tlp:amber · 6/26/2026, 5:14:30 PM

[$] Initiating writeback earlier Writeback is the process of ensuring that dirty pages or folios in the page cache are flushed to the disk, so that changes to those files are made persistent. In a filesystem-track session at the 2026 Linux Storage, Filesystem, Memory Management, and BPF Summit , Jeff Layton wanted to discuss whether the writeback operation should be initiated earlier than it is today. The consensus seemed to be that it should be done earlier, but the path to…

lwn_kernel · tlp:amber · 6/26/2026, 2:56:46 PM

Lots of stories about systemd v261 Lennart Poettering has posted a list of Mastodon posts about the changes in the systemd v261 release. The Mastodon format makes the reading harder, but there is a lot of useful information there. Lots of stories about systemd v261 [LWN.net] LWN .net News from the source Content Weekly Edition Archives Search Kernel Security Events calendar Unread comments LWN FAQ Write for us User: Password: | | Log in / Subscribe / Register Lots of storie…

chainalysis · tlp:amber · 6/26/2026, 2:38:22 PM

Inside a Sandwich Attack: Lessons From the $7.5 Million Heist Against JaredfromSubway.eth Summary JaredfromSubway.eth, the most prolific sandwich-attack bot on Ethereum, was drained of at least $7.5 million in a reverse honeypot… The post Inside a Sandwich Attack: Lessons From the $7.5 Million Heist Against JaredfromSubway.eth appeared first on Chainalysis . Sandwich Attack: How JaredfromSubway Lost $7.5M - Chainalysis Chainalysis Products Crypto Investigations Invest…

lwn_kernel · tlp:amber · 6/26/2026, 2:03:28 PM

[$] What's coming in Git 2.55 The Git v2.55.0-rc2 testing release appeared on June 23, suggesting that the final Git 2.55 release can be expected in the near future. While this Git update lacks radical new features, it does include a number of improvements that regular Git users will appreciate, including commands to easily edit the commit history, more formatting options, fsmonitor support for Linux, and more.

lwn_kernel · tlp:amber · 6/26/2026, 1:19:28 PM

Security updates for Friday Security updates have been issued by AlmaLinux (buildah, coreutils, evince, libpng, libreoffice, libtasn1, libxml2, libxslt, nginx, nginx:1.24, nginx:1.26, postgresql:12, python-urllib3, python3.12-urllib3, python3.14, python3.14-urllib3, skopeo, tigervnc, tomcat, and vim), Debian (chromium, dnsdist, giflib, libdbi-perl, libssh2, libtext-csv-xs-perl, pdns, pdns-recursor, python-urllib3, and sogo), Fedora (goose, httpd, librabbitmq, perl-Compress-R…

lwn_kernel · tlp:amber · 6/26/2026, 1:11:29 PM

The "Akrites" vulnerability-mitigation project launches The Linux Foundation, in a letter co-signed by a large range of organizations and companies, has announced the launch of "Akrites", a project to fast-track vulnerability fixes into projects. As Akrites works upstream to fix projects at the source, we commit to support downstream efforts to secure critical infrastructure before it can be exploited. When patches are released to the public, adversaries are able to utilize …

cisa_alerts · tlp:amber · 6/26/2026, 12:00:00 PM

Russian Intelligence Services Continue to Target Commercial Messaging Applications CISA and the Federal Bureau of Investigation (FBI) issued an updated Public Service Announcement (PSA) warning of Russian Intelligence Services (RIS) cyber threat actors targeting commercial messaging applications in ongoing phishing campaigns. This PSA is an update to the March 2026 Russian Intelligence Services Target Commercial Messaging Application Accounts and provides recent tactics, rec…

eset · tlp:amber · 6/26/2026, 8:50:00 AM

SMB cyber readiness: the road to resilience starts here Your business may be small, but its attack surface is anything but. Readiness is the first step to resilience. SMB cyber readiness: the road to resilience starts here Award-winning news, views, and insight from the ESET security community English Español Deutsch Português Français TIPS & ADVICE BUSINESS SECURITY ESET RESEARCH About ESET Research Blogposts Podcasts White papers Threat reports WeLiveScience FEATURED …

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities? arXiv:2606.26216v1 Announce Type: new Abstract: We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability detection, exploit generation, and patch synthesis. Built from 541 real-world exploit incidents from DeFiHackLabs spanning 9 EVM chains, the benchmark provides end-to-end on-chain evalu…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model arXiv:2606.26373v1 Announce Type: new Abstract: Dense embeddings power semantic search and retrieval-augmented generation, but embedding-inversion attacks can reconstruct source text from a vector: when a vector database leaks, the documents behind it leak too. The textbook defences are extremes - encrypting the whole search homomorphically…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models arXiv:2606.26285v1 Announce Type: new Abstract: Noise-based backdoor attacks on diffusion models typically rely on input-time trigger injection, untargeted activation, and out-of-distribution target generation. Such assumptions reduce both the stealthiness and the practical relevance of these attacks. In this work, we present TEMPO-Diffusion, a targeted backdoor framework that localizes the malicious…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Beyond Takedown: Measuring Malicious Go Module Persistence in the Wild arXiv:2606.26291v1 Announce Type: new Abstract: We measure an automation-based supply chain campaign in the Go ecosystem. The attackers repackage legitimate Go modules under attacker-controlled owners, and embed them with obfuscated code for an import-triggered downloader. Our results come from two complementary analyses: a) a manual search on GitHub across 2,113 repositories and b) a large-scale scan of …

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Expecting (Targeted Ads)? Network Analysis of User Health Data Leakage in Fertility Tracking Apps arXiv:2606.26276v1 Announce Type: new Abstract: While human factors in the privacy of fertility tracking apps -- health trackers that record user's menstrual or pregnancy data -- has been the subject of extensive study, little attention has been paid to the technical aspects of apps' data handling practices. We conduct a network-based measurement study of a corpus of 20 Android …

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

MIRAGE: Protecting against Malicious Image Editing via False Moderation arXiv:2606.26199v1 Announce Type: new Abstract: The proliferation of AI-powered image editing systems raises serious concerns because it allows personal images to be arbitrarily manipulated at scale, with minimal effort, and a lower barrier to entry. Prior work on image immunization adds imperceptible perturbations to an image to protect against unauthorized manipulations. However, these methods usually …

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Data Facts: A Metadata Schema for Structured Data Exchange in the NANDini Multi-Agent Ecosystem arXiv:2606.26211v1 Announce Type: new Abstract: NANDini (Networked Agents Natural Distillation of Interconnected Nodal Intelligence) envisions an automated ecosystem where intelligent agents independently create, process, and exchange data to drive decisions at scale. Realizing this vision requires infrastructure beyond agent discovery and communication: agents must be able to adv…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models arXiv:2606.26566v1 Announce Type: new Abstract: Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LLMs), diffusion-based attacks on image classifiers, jailbreak pipelines against vision-language models, and diffusion-based input purification …

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents arXiv:2606.26627v1 Announce Type: new Abstract: Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data, privacy becomes harder to enforce. An agent touches many data sources, runs multi-step workflows, keeps state across sessi…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Lessons from the Adoption and Deprecation of the Privacy Sandbox Web APIs arXiv:2606.26390v1 Announce Type: new Abstract: While several web actors have been trying to reduce web tracking for years, it remains unclear how to achieve both desirable levels of utility and privacy. In 2019, Google launched the Privacy Sandbox initiative to balance that trade-off and find privacy alternatives to common use cases such as advertising. Yet, in late 2025, Google canceled the project a…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems arXiv:2606.26664v1 Announce Type: new Abstract: Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes and making them incompatible with dynamic, large-scale financial graphs. We propose TGHE (Template-based Graph Homomorphic Encryption), an ego-…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills arXiv:2606.26524v1 Announce Type: new Abstract: Agentic systems increasingly act through third-party skills, allowing model-generated decisions to affect files, communication channels, and cyber-physical devices. These skills often include natural-language specifications that define access permissions, disclosure limits, execution privileges, and required preconditions. Although such specifications de…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

The Fungible Reserve Standard: A Deterministic Framework for Encoding Carrying Costs in Asset-Backed Tokens arXiv:2606.26704v1 Announce Type: new Abstract: The tokenization of real-world assets (RWAs) has emerged as a transformative application of blockchain technology, with market projections estimating trillions of dollars in tokenized assets within the coming decade. However, a fundamental challenge remains unaddressed: physical assets such as precious metals, stored comm…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities arXiv:2606.26933v1 Announce Type: new Abstract: AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms memory violations and efficiently filters false positives. Many dangerous vulnerability classes, such as cryptographic misuse, however, lack any comparable instrumentation. In this work, we present Chai, an AI-based system that discovers and v…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors arXiv:2606.26707v1 Announce Type: new Abstract: Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors. In this work, we first show that, despite claims, existing problem-space attacks remain largely impractical. Most techniques leverage software transplantation to inject entire benign modules, introducing man…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

DKVE: Decentralized Key Validation for End-to-End Encrypted Messaging arXiv:2606.26486v1 Announce Type: new Abstract: End-to-end encrypted messaging systems depend on authentic public key distribution to prevent man-in-the-middle (MitM) attacks. Current solutions present a stark trade-off: out-of-band (OOB) verification provides strong security but lacks scalability for large contact lists, while key transparency (KT) systems enable automated verification at high storage cos…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats arXiv:2606.26377v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in interactive applications, yet they remain vulnerable to adversarial interactions that induce harmful, deceptive, or policy-violating outputs. Existing defenses typically analyze either user prompts or generated outputs, but not both. However, many real-world attacks exploit a separation between ad…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents arXiv:2606.26479v1 Announce Type: new Abstract: Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training the model to refuse malicious instructions, enforce security outside the model with a deterministic policy that mediates the agent's actions. Systems such as CaMeL, FIDES, Progent, RTBAS, and FORGE rea…

arxiv_cs_cr · tlp:amber · 6/26/2026, 4:00:00 AM

MergeLLL: A Hierarchical Divide-and-Conquer Framework for LLL-Based Lattice Reduction arXiv:2606.26784v1 Announce Type: new Abstract: Lattice basis reduction algorithms have various applications in computational number theory and lattice-based cryptography, but their complexity increases rapidly with the dimension. Motivated by the divide-and-conquer strategy of merge sort and incorporating PotLLL-style deep insertions during recombination, MergeLLL is proposed. In this fram…