Latest threat reports & articles

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

TENNOR: Trustworthy Execution for Neural Networks through Obliviousness and Retrievals arXiv:2605.07160v1 Announce Type: new Abstract: Training wide neural networks on sensitive data in untrusted cloud environments requires simultaneously achieving computational efficiency and rigorous privacy guarantees. Sparsification techniques, essential for scalable training of wide layers, expose input-dependent memory-access patterns (i.e., leakage) that are visible and can be exploit…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Asymmetric Phase Coding Audio Watermarking arXiv:2605.07241v1 Announce Type: new Abstract: The proliferation of deepfake audio challenges voice-based authentication systems; passive forensic detectors are sensitive to evolving generative models and to real-world channel distortions. We propose Asymmetric Phase Coding (APC), a training-free cryptographic signing layer for audio, designed as a compact and auditable provenance primitive that can stand alone or be stacked with l…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions arXiv:2605.07135v1 Announce Type: new Abstract: GitHub Actions is increasingly used to deploy LLM-based agents for repository-centric tasks such as issue triage, pull-request review, code modification, and release assistance. These agentic workflows extend traditional CI/CD automation with agentic capabilities but also create a new injection surface. In this paper, we introduce Agentic Wo…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Benchmarking Large Language Models for IoC Recovery under Adversarial Code Obfuscation and Encryption arXiv:2605.06910v1 Announce Type: new Abstract: Software obfuscation and encryption present persistent challenges for program comprehension and security analysis, particularly when adversaries conceal Indicators of Compromise (IoCs) such as IP addresses within source code. While Large Language Models (LLMs) have recently demonstrated remarkable progress in code reasoning and…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Membership Inference Attacks on Vision-Language-Action Models arXiv:2605.07088v1 Announce Type: new Abstract: Membership inference attacks (MIAs) have been extensively studied in large language models (LLMs) and vision-language models (VLMs), yet their implications for vision-language-action (VLA) models remain largely unexplored. VLA models differ from standard LLMs and VLMs in several important ways: they are often fine-tuned for many epochs on relatively small embodied da…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Beyond the Wrapper: Identifying Artifact Reliance in Static Malware Classifiers using TRUSTEE arXiv:2605.07034v1 Announce Type: new Abstract: Modern cybersecurity relies heavily on static machine-learning-based malware classifiers. However, transformations such as packing and other non-semantic modifications applied to executable files limit their reliability. Malware classifiers often learn these unnecessary artifacts rather than the true binary behavior because of the high…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Combating Organized Platform Abuse: Amplifying Weak Risk Signals with Structural Information arXiv:2605.07383v1 Announce Type: new Abstract: Large-scale online service platforms face severe challenges from organized platform abuse: multiple forms such as credit card fraud and promotion abuse continually emerge, characterized by large numbers of involved accounts, rapid outbreaks, and constantly shifting tactics. Existing mainstream approaches, whether heuristic rules limited…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

When the Ruler is Broken: Parsing-Induced Suppression in LLM-Based Security Log Evaluation arXiv:2605.07293v1 Announce Type: new Abstract: LLM-based SOC log classifiers are commonly evaluated using regular-expression pipelines that extract structured fields from free-form model output. We demonstrate that this practice introduces a class of silent, systematic evaluation errors, which we term parsing-induced suppression that can cause a fully functional model to appear comple…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Aquaman: A Transparent Proxy Architecture for Quantum Resilient Key Establishment arXiv:2605.06932v1 Announce Type: new Abstract: The harvest-now, decrypt-later (HNDL) threat--adversaries intercepting and archiving ciphertext today for retrospective decryption once quantum computers mature--turns the future quantum threat into a present liability for the public-key primitives (RSA, Diffie-Hellman, ECC) that anchor modern session-key exchange. We present Aquaman, a transparen…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Zombies in Alternate Realities: The Afterlife of Domain Names in DNS Integrations arXiv:2605.06880v1 Announce Type: new Abstract: DNS integrations leverage the discovery, trust, and uniqueness of the global Domain Name System with a linkage to another naming ecosystem, so the DNS name can help identify resources such as a cryptocurrency wallet or software component. While DNS ownership is verified at linkage creation, many ecosystems do not track subsequent DNS changes. The …

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

A Unified Open-Set Framework for Scalable PUF-Based Authentication of Heterogeneous IoT Devices arXiv:2605.07340v1 Announce Type: new Abstract: As modern cyber systems scale to include large populations of heterogeneous IoT devices, securing them against impersonation and forgery is a critical cybersecurity challenge. Physical Unclonable Functions (PUFs) offer a lightweight, hardware-rooted trust anchor for IoT security. However, different PUF architectures possess distinct …

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

The Cost of Quantum Resistance: A Hash-Based Commit-Reveal Alternative for Minimizing Blockchain Infrastructure Overhead arXiv:2605.06853v1 Announce Type: new Abstract: The transition to post-quantum cryptography in blockchain systems such as Bitcoin and Ethereum is often framed as a purely cryptographic problem. In practice, it also presents significant economic and infrastructural challenges: in globally replicated networks, increases in transaction size and verification c…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

From Conceptual Scaffold to Prototype: A Standardized Zonal Architecture for Wi-Fi Security Training arXiv:2605.07400v1 Announce Type: new Abstract: Wi-Fi is the dominant wireless access technology, but its widespread use also exposes systems to threats such as rogue access points, deauthentication attacks, and other IEEE 802.11-specific vulnerabilities. Although Cyber Ranges (CRs) have become valuable platforms for cybersecurity training and experimentation, existing wirele…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Agentic AI and the Industrialization of Cyber Offense: Forecast, Consequences, and Defensive Priorities for Enterprises and the Mittelstand arXiv:2605.06713v1 Announce Type: new Abstract: Agentic AI systems can plan, call tools, inspect code, interact with web applications, and coordinate multi-step workflows. These same capabilities change the economics of cyber offense. The central near-term risk is not that every low-skill criminal immediately becomes a frontier exploit r…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Narrow Secret Loyalty Dodges Black-Box Audits arXiv:2605.06846v1 Announce Type: new Abstract: Recent work identifies secret loyalties as a distinct threat from standard backdoors. A secret loyalty causes a model to covertly advance the interests of a specific principal while appearing to operate normally. We construct the first model organisms of narrow secret loyalties. We fine-tune Qwen-2.5-Instruct at three scales (1.5B, 7B, 32B) to encourage users towards extreme harmful…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

PAMPOS: Causal Transformer-based Trajectory Prediction for Attack-Agnostic Misbehavior Detection in V2X Networks arXiv:2605.06833v1 Announce Type: new Abstract: Misbehavior detection in Vehicle-to-Everything (V2X) networks is a second line of defense against insider falsification attacks that cryptographic mechanisms alone cannot address. Existing learning-based Misbehavior Detection Schemes (MDSs) are supervised, requiring labeled attack samples at training time, thus faili…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

TUANDROMD-X: Advanced Entropy and Visual Analytics Dataset for Enhanced Malware Detection and Classification arXiv:2605.06718v1 Announce Type: new Abstract: Malware and malware-based attacks are becoming more prevalent and complex. Attackers regularly come up with new techniques that have the ability to evade conventional and signature-based malware defense. In order to address such threats, there is an increasing demand for advanced and better defense solutions. Machine lea…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

Language Models Can Autonomously Hack and Self-Replicate arXiv:2605.06760v1 Announce Type: new Abstract: We demonstrate that language models can autonomously replicate their weights and harness across a network by exploiting vulnerable hosts. The agent independently finds and exploits a web-application vulnerability, extracts credentials, and deploys an inference server with a copy of its harness and prompt on the compromised host. We test four vulnerability classes: hash by…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

A UEFI System with SPDM to Protect Against Unauthorized Device Connections arXiv:2605.06744v1 Announce Type: new Abstract: Attackers willing to compromise computing systems can use malicious peripherals as an attack vector, threatening users that cannot verify the hardware's authenticity. To address this problem, our work uses the Security Protocol and Data Model to propose a UEFI system capable of authenticating PCIe and USB devices trying to connect with it. We also develo…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

From Specification to Deployment: Empirical Evidence from a W3C VC + DID Trust Infrastructure for Autonomous Agents arXiv:2605.06738v1 Announce Type: new Abstract: Autonomous AI agents now transact at production scale -- 69,000 bots executing 165 million transactions across 50 million USDC in cumulative volume on a single marketplace -- without any shared trust layer between participants. Regulatory frameworks (Singapore IMDA, NIST CAISI, EU AI Act) and major AI laboratories…

arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM

When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents arXiv:2605.06731v1 Announce Type: new Abstract: Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an agent's long-term state, inadvertently weakening future confirmation boundaries, expanding tool-use d…

trend_micro · tlp:amber · 5/11/2026, 12:00:00 AM

Vibe Hacking: Two AI-Augmented Campaigns Target Government and Financial Sectors in Latin America TrendAI™ Research has identified two emerging threat campaigns—SHADOW-AETHER-040 and SHADOW-AETHER-064—that use agentic AI to drive intrusion operations against government and financial organizations in Latin America, marking these among the first cases we have observed of AI agents executing attacks from initial access to data exfiltration. Vibe Hacking: Two AI-Augmented Campa…

lwn_kernel · tlp:amber · 5/10/2026, 11:23:10 PM

Kernel prepatch 7.1-rc3 Linus has released 7.1-rc3 for testing. " I think this answers the 'is 7.1 continuing the larger size pattern that we saw with 7.0?' question, and the answer is yes: that wasn't a fluke brought on by a .0 release - it simply seems to be the new normal. " Kernel prepatch 7.1-rc3 [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 …

huggingface_blog · tlp:amber · 5/10/2026, 6:44:11 PM

MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Log In Sign Up Back to Articles MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X Team Article Published May 10, 2026 Upvote 1 Syed Muhammad Sarmad sarmaddev Follow lablab-ai-amd-developer-hackathon The Problem We Sol…

trend_micro · tlp:amber · 5/10/2026, 12:00:00 AM

What Is the Instructure Canvas Breach? Impact, Risks, and What Institutions Should Do The Instructure Canvas breach affects universities, K–12 school districts, and teaching hospitals globally. This blog entry intends to provide context and practical guidance. What Is the Instructure Canvas Breach? Impact, Risks, and What Institutions Should Do | Trend Micro (US) search close About Mission and Culture Mission and Culture As a leader in the AI-driven shift, we are committed …

lwn_kernel · tlp:amber · 5/8/2026, 7:50:34 PM

More stable kernels with partial Dirty Frag fixes Greg Kroah-Hartman has released the 6.1.171 , 5.15.205 , and 5.10.255 stable kernels, quickly followed by 6.1.172 and 5.15.206 kernels. This is another round of stable kernels to provide fixes for one of the CVEs ( CVE-2026-43284 ) assigned following the Dirty Frag and Copy Fail 2 security disclosures. There is not, yet, a stable kernel with a fix for CVE-2026-43500 , though a patch to fix the second half is in the …

ars_security · tlp:amber · 5/8/2026, 6:33:48 PM

Chaos erupts as cyberattack disrupts learning platform Canvas amid finals Across the country, schools and colleges postpone year-end tests. Chaos erupted at schools and colleges throughout the US on Thursday as a cyberattack disrupted online learning platform Canvas just as students were due to take final exams. Canvas parent company Instructure said that as of Friday morning, the platform was back online. Instructure said it temporarily took Canvas offline on Thursday afte…

microsoft_mstic · tlp:amber · 5/8/2026, 5:12:46 PM

Active attack: Dirty Frag Linux vulnerability expands post-compromise risk Dirty Frag is a newly disclosed Linux local privilege escalation vulnerability affecting kernel networking and memory-fragment handling components including esp4, esp6, and rxrpc. The vulnerability enables reliable escalation from an unprivileged user to root and may be leveraged after initial compromise through SSH access, web shells, containers, or low-privileged accounts. Microsoft Defender is acti…

lwn_kernel · tlp:amber · 5/8/2026, 4:30:46 PM

[$] Forgejo "carrot disclosure" raises security questions An unusual, some might say hostile, approach to disclosing an alleged remote-code-execution (RCE) flaw in the Forgejo software-collaboration platform has sparked a multifaceted conversation. A so-called " carrot disclosure " in April has raised questions about the researcher's methods of unveiling a security problem, Forgejo's security policies, and the project's overall security posture.

huggingface_blog · tlp:amber · 5/8/2026, 4:03:50 PM

EMO: Pretraining mixture of experts for emergent modularity EMO: Pretraining mixture of experts for emergent modularity Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Log In Sign Up Back to Articles EMO: Pretraining mixture of experts for emergent modularity Team Article Published May 8, 2026 Upvote 22 +16 Kyle Wiggers Ai2Comms Follow allenai Ryan Wang ryanyxw Follow allenai How do we get modularity to emerge? Benchmark results What are expert subset…

lwn_kernel · tlp:amber · 5/8/2026, 1:36:05 PM

killswitch for short-term emergency vulnerability mitigation It seems that we are in for an extended period of the disclosure of vulnerabilities before fixes become available. One possible way of coping with this flood might be the killswitch proposal from Sasha Levin. In short, killswitch can immediately disable access to specific functionality in a running kernel, essentially blasting a vulnerable path (and its associated functionality) out of existence until a fix can be …

lwn_kernel · tlp:amber · 5/8/2026, 1:20:57 PM

[$] A 2026 DAMON update The kernel's DAMON subsystem provides user-space monitoring and management of system memory. DAMON is developing rapidly, so an update on its progress has become a regular feature of the annual Linux Storage, Filesystem, Memory Management, and BPF Summit . This tradition continued at the 2026 gathering with an update from DAMON creator SeongJae Park covering a long list of new capabilities — tiering, data attributes monitoring, transparent huge pages,…

lwn_kernel · tlp:amber · 5/8/2026, 1:13:53 PM

Security updates for Friday Security updates have been issued by AlmaLinux (libsoup and mingw-libtiff), Debian (apache2, chromium, lcms2, libreoffice, and prosody), Fedora (openssl and perl-Starman), Oracle (git-lfs, libsoup, and perl-XML-Parser), Slackware (libgpg, mozilla, and php), SUSE (389-ds, cairo, cf-cli, chromedriver, cri-tools, freeipmi, gnutls, grafana, java-11-openjdk, java-17-openjdk, jetty-minimal, libmariadbd-devel, librsvg, mesa, mozjs52, mutt, nix, opencrypt…

cisa_alerts · tlp:amber · 5/8/2026, 12:00:00 PM

CISA Adds One Known Exploited Vulnerability to Catalog CISA has added one new vulnerability to its  Known Exploited Vulnerabilities (KEV) Catalog , based on evidence of active exploitation. CVE-2026-42208  BerriAI LiteLLM SQL Injection Vulnerability This type of vulnerability is a frequent attack vector for malicious cyber actors and poses significant risks to the federal enterprise. Binding Operational Directive (B…

lwn_kernel · tlp:amber · 5/8/2026, 9:49:05 AM

Four stable kernels with partial fixes for Dirty Frag Greg Kroah-Hartman has announced the release of the 7.0.5 , 6.18.28 , 6.12.87 , and 6.6.138 stable kernels. These kernels contain a partial fix for the Dirty Frag and Copy Fail 2 security flaws. Kroah-Hartman has confirmed that a second patch is required, but it is still in development and has not yet been merged. Four stable kernels with partial fixes for Dirty Frag [LWN.net] LWN .net News from the source Cont…

lwn_kernel · tlp:amber · 5/7/2026, 8:25:43 PM

Dirty Frag: a zero-day universal Linux LPE Hyunwoo Kim has announced the Dirty Frag security flaw, a local-privilege-escalation (LPE) vulnerability similar to the recently disclosed Copy Fail flaw: Because the embargo has now been broken, no patches or CVEs exist for these vulnerabilities. After consultation with the linux-distros@vs.openwall.org maintainers, and at the maintainers' request, I am publicly releasing this Dirty Frag document. As with the previous Copy Fail vul…

microsoft_mstic · tlp:amber · 5/7/2026, 8:22:39 PM

When prompts become shells: RCE vulnerabilities in AI agent frameworks New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these vulnerabilities work, what’s impacted, and how to secure your agents. The post When prompts become shells: RCE vulnerabilities in AI agent frameworks appeared first on Microsoft Security Blog . In this article A representative case study: Semantic Kernel CVE-2026-26030: In-Memory Vector Sto…

ars_security · tlp:amber · 5/7/2026, 7:18:16 PM

Mozilla says 271 vulnerabilities found by Mythos have "almost no false positives" The developer of Firefox says it has "completely bought in" on AI-assisted bug discovery. The disbelief was palpable when Mozilla’s CTO last month declared that AI-assisted vulnerability detection meant “ zero-days are numbered ” and “defenders finally have a chance to win, decisively.” After all, it looked like part of an all-too-familiar pattern: Cherry-pick a handful of impressive AI-achiev…