REPORTS
Fresh threat intelligence we ingest from public vendor and research feeds — each report linked to its original source. Search, filter by source, and open the reference.
Reports
Newest first. Search, filter by source, open the original.
2281 reports · page 49 of 58
arxiv_cs_cr · tlp:amber · 5/13/2026, 4:00:00 AM
Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents arXiv:2605.11032v1 Announce Type: new Abstract: We present Portable Agent Memory, an open protocol and reference implementation for transferring persistent memory state across heterogeneous AI agents. Modern AI agents accumulate rich context -- episodic events,semantic knowledge, procedural skills, working state, and identity preferences -- but this context remains…
Read original ↗https://arxiv.org/abs/2605.11032arxiv_cs_cr · tlp:amber · 5/13/2026, 4:00:00 AM
FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments arXiv:2605.11029v1 Announce Type: new Abstract: An attacker can split a malicious goal into sub-prompts that each look benign on their own and only become harmful in combination. Existing LLM safety benchmarks evaluate prompts one at a time, or across turns of a single chat, and so do not look for a malicious signal spread across separate sessions with no shared context. We build FragBench, a benchmark drawn…
arxiv_cs_cr · tlp:amber · 5/13/2026, 4:00:00 AM
AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents arXiv:2605.11026v1 Announce Type: new Abstract: Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such as Kurdish and Arabic without tested protection. This pa…
Read original ↗https://arxiv.org/abs/2605.11026arxiv_cs_cr · tlp:amber · 5/13/2026, 4:00:00 AM
DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization arXiv:2605.11015v1 Announce Type: new Abstract: Software vulnerability detection plays a critical role in ensuring system security, where real-world auditing requires not only determining whether a function is vulnerable but also pinpointing the specific lines responsible. However, existing approaches either rely on a single information source -- sequential, structural, or semantic -- fa…
Read original ↗https://arxiv.org/abs/2605.11015arxiv_cs_cr · tlp:amber · 5/13/2026, 4:00:00 AM
The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents arXiv:2605.11003v1 Announce Type: new Abstract: This position paper argues that the Authorization-Execution Gap (AEG) is a major safety and security problem in open-world agents. The AEG is the divergence between what a principal intends to authorize and what an open-world agent ultimately executes. Because such agents act autonomously across tools, persistent state, and multi-agent h…
Read original ↗https://arxiv.org/abs/2605.11003arxiv_cs_cr · tlp:amber · 5/13/2026, 4:00:00 AM
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks arXiv:2605.11002v1 Announce Type: new Abstract: Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer. Recent methods demonstrate this risk, but they are usually evaluated as black-box pipelines with different budget…
Read original ↗https://arxiv.org/abs/2605.11002arxiv_cs_cr · tlp:amber · 5/13/2026, 4:00:00 AM
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks arXiv:2605.10977v1 Announce Type: new Abstract: Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as paraphrasing. We propose PASA, a principled, robust, and distortion-free waterm…
Read original ↗https://arxiv.org/abs/2605.10977trend_micro · tlp:amber · 5/13/2026, 12:00:00 AM
Analyzing TeamPCP’s Supply Chain Attacks: Checkmarx KICS and elementary-data in CI/CD Credential Theft Our research examines the April 22 Checkmarx KICS and April 24 elementary-data incidents as part of a broader TeamPCP supply chain campaign. Across both cases, the actor abused trusted CI/CD and release workflows to steal credentials at scale. Analyzing TeamPCP’s Supply Chain Attacks: Checkmarx KICS and elementary-data in CI/CD Credential Theft | Trend Micro (US) search cl…
Read original ↗https://www.trendmicro.com/en_us/research/26/e/analyzing-teampcp-supply-chain-attacks.htmlmicrosoft_mstic · tlp:amber · 5/12/2026, 10:53:09 PM
Accelerating detection engineering using AI-assisted synthetic attack logs generation What if you could generate realistic attack telemetry on demand? Explore research methods that translate attacker behaviors (TTPs) into synthetic logs that can trigger detections at scale and without sensitive data. The post Accelerating detection engineering using AI-assisted synthetic attack logs generation appeared first on Microsoft Security Blog . In this article Core Idea: From TTPs …
Read original ↗https://www.microsoft.com/en-us/security/blog/2026/05/12/accelerating-detection-engineering-using-ai-assisted-synthetic-attack-logs-generationmicrosoft_mstic · tlp:amber · 5/12/2026, 10:00:00 PM
Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark Today Microsoft is announcing a major step forward in AI-powered cyber defense: a new multi-model agentic scanning harness (codenamed MDASH). The post Defense at AI speed: Microsoft’s new multi-model agentic security system tops leading industry benchmark appeared first on Microsoft Security Blog . In this article AI-powered vulnerability discovery at hyper-scale Codenam…
Read original ↗https://www.microsoft.com/en-us/security/blog/2026/05/12/defense-at-ai-speed-microsofts-new-multi-model-agentic-security-system-tops-leading-industry-benchmarktalos · tlp:amber · 5/12/2026, 7:57:04 PM
Microsoft Patch Tuesday for May 2026 — Snort rules and prominent vulnerabilities Microsoft has released its monthly security update for May 2026, which includes 112 vulnerabilities affecting a range of products, including 16 that Microsoft marked as “critical”. By   Jaeson Schultz   Microsoft has released its monthly security update for May 2026, which includes 137 vulnerabilities affecting a range of products, including 31 that Microsoft …
Read original ↗https://blog.talosintelligence.com/microsoft-patch-tuesday-may-2026lwn_kernel · tlp:amber · 5/12/2026, 5:25:31 PM
[$] Using dma-bufs for read and write operations The kernel's dma-buf subsystem provides a way for drivers to share memory buffers, usually in order to support efficient device-to-device I/O . At the 2026 Linux Storage, Filesystem, Memory Management, and BPF Summit , Pavel Begunkov, assisted by Kanchan Joshi, led a joint session of the storage and memory-management tracks to explore ways to make the use of dma-bufs more efficient yet, and to make them available for read and …
Read original ↗https://lwn.net/Articles/1072317microsoft_mstic · tlp:amber · 5/12/2026, 4:00:00 PM
Defending consumer web properties against modern DDoS attacks Read how to protect consumer websites and defend against modern DDoS attacks with layered security, resilient architecture, and graceful service degradation. The post Defending consumer web properties against modern DDoS attacks appeared first on Microsoft Security Blog . If you own, create, or maintain online services and web portals, you’re probably aware of the dramatic upswing in DDoS attacks on your domains.…
Read original ↗https://www.microsoft.com/en-us/security/blog/2026/05/12/defending-consumer-web-properties-against-modern-ddos-attacksmicrosoft_mstic · tlp:amber · 5/12/2026, 3:00:00 PM
Undermining the trust boundary: Investigating a stealthy intrusion through third-party compromise Microsoft Incident Response investigated an attack operated through legitimate and trusted administrative mechanisms to blend seamlessly into routine operations and remain undetected demonstrating that intrusions have increasingly avoided using noisy exploits, obvious malware, or custom tooling, instead leveraging systems that organizations already trust within their environment…
Read original ↗https://www.microsoft.com/en-us/security/blog/2026/05/12/undermining-the-trust-boundary-investigating-a-stealthy-intrusion-through-third-party-compromiselwn_kernel · tlp:amber · 5/12/2026, 1:24:49 PM
[$] Scaling transparent huge pages to 1GB As a general rule, when developers talk about huge pages, they are referring to PMD-level pages that are 1MB or 2MB in size, depending on the CPU architecture. Most CPUs can support other huge-page sizes, though. On x86 systems, PUD-level huge pages hold 1GB of data. Providing such large pages transparently to processes has generally not been considered as either feasible or desirable, but Usama Arif is trying to change that assessme…
Read original ↗https://lwn.net/Articles/1071716lwn_kernel · tlp:amber · 5/12/2026, 1:17:34 PM
Security updates for Tuesday Security updates have been issued by AlmaLinux (freerdp, glib2, libsoup3, and openexr), Debian (dnsmasq, p7zip, p7zip-rar, python-authlib, and rails), Fedora (chromium, firefox, httpd, and nss), SUSE (java-25-openj9, krb5, libmodsecurity3, and mcphost), and Ubuntu (imagemagick, linux, linux-aws, linux-aws-fips, linux-aws-hwe, linux-azure-4.15, linux-fips, linux-gcp, linux-gcp-4.15, linux-gcp-fips, linux-hwe, linux-kvm, linux-oracle, linux-azure, …
Read original ↗https://lwn.net/Articles/1072498cisa_alerts · tlp:amber · 5/12/2026, 12:00:00 PM
ABB WebPro SNMP Card PowerValue Multiple Vulnerabilities View CSAF Summary ABB became aware of multiple internally discovered vulnerabilities in the WebPro SNMP card PowerValue for the product versions listed as affected in the advisory. Depending upon the vulnerability, an attacker with access to local network who successfully exploited this vulnerability could have - Unauthorized access - Insufficient Session Expiration leading to resource unavailability - Uncontrolled Res…
Read original ↗https://www.cisa.gov/news-events/ics-advisories/icsa-26-132-06cisa_alerts · tlp:amber · 5/12/2026, 12:00:00 PM
ABB AC500 V3 Stack Buffer Overflow in Cryptographic Message Syntax View CSAF Summary ABB became aware of vulnerability in the products versions listed as affected in the advisory. An update is available that resolves publicly reported vulnerability. An attacker who successfully exploited these vulnerabilities could cause a crash, denial-of-service (DoS), or potentially remote code execution. The following versions of ABB AC500 V3 Stack Buffer Overflow in Cryptographic Messag…
Read original ↗https://www.cisa.gov/news-events/ics-advisories/icsa-26-132-05cisa_alerts · tlp:amber · 5/12/2026, 12:00:00 PM
Fuji Electric Tellus View CSAF Summary Successful exploitation of this vulnerability could allow an attacker to elevate privileges from user to system, which may then enable the attacker to cause a temporary denial of service, open files, or delete files. The following versions of Fuji Electric Tellus are affected: Tellus 5.0.2 CVSS Vendor Equipment Vulnerabilities v3 7.8 Fuji Electric Fuji Electric Tellus Exposed Dangerous Method or Function Background Critical Infrastructu…
Read original ↗https://www.cisa.gov/news-events/ics-advisories/icsa-26-132-01cisa_alerts · tlp:amber · 5/12/2026, 12:00:00 PM
ABB Automation Builder Gateway for Windows View CSAF Summary ABB became aware of severe vulnerability in the products versions listed as affected in the advisory. The Windows gateway is accessible remotely by default. Unauthenticated attackers can therefore search for PLCs, but the user management of the PLCs prevents the actual access to the PLCs – unless it is disabled The following versions of ABB Automation Builder Gateway for Windows are affected: Automation Builder <…
Read original ↗https://www.cisa.gov/news-events/ics-advisories/icsa-26-132-04cisa_alerts · tlp:amber · 5/12/2026, 12:00:00 PM
Subnet Solutions PowerSYSTEM Center View CSAF Summary Successful exploitation of these vulnerabilities could allow an authenticated attacker to expose sensitive information or cause a CRLF injection. The following versions of Subnet Solutions PowerSYSTEM Center are affected: PowerSYSTEM Center 2020 <=5.28.x (CVE-2026-35504) PowerSYSTEM Center 2020 >=5.8.x|<=5.28.x (CVE-2026-26289) PowerSYSTEM Center 2020 >=5.11.x|<=5.28.x (CVE-2026-33570) PowerSYSTEM Center 20…
Read original ↗https://www.cisa.gov/news-events/ics-advisories/icsa-26-132-02cisa_alerts · tlp:amber · 5/12/2026, 12:00:00 PM
ABB AC500 V3 Multiple Vulnerabilities View CSAF Summary ABB became aware of severe vulnerability in the products versions listed as affected in the advisory. An update is available that resolves these vulnerabilities. An attacker who successfully exploited these vulnerabilities could bypass the user management and read visualization files (CVE-2025-2595), read and write certificates and keys (CVE-2025-41659) or cause a denial-of-service (DoS) (CVE-2025-41691). The following …
Read original ↗https://www.cisa.gov/news-events/ics-advisories/icsa-26-132-03cisa_alerts · tlp:amber · 5/12/2026, 12:00:00 PM
Software Bill of Materials for AI - Minimum Elements CISA and the Group of Seven (G7) international partners—Germany, Canada, France, Italy, Japan, the United Kingdom, and the European Union—have released joint guidance, Software Bill of Materials for AI – Minimum Elements , to help public and private sector stakeholders improve transparency in their artificial intelligence (AI) systems and supply chains. A software bill of materials (SBOM) acts as an “ingredients list…
Read original ↗https://www.cisa.gov/resources-tools/resources/software-bill-materials-ai-minimum-elementstrail_of_bits · tlp:amber · 5/12/2026, 11:00:00 AM
Go fuzzing was missing half the toolkit. We forked the toolchain to fix it. Go’s native fuzzing is useful, but it stands far behind state-of-the-art tooling that the Rust, C, and C++ ecosystems offer with LibAFL and AFL++. Path constraints are hard to solve. Structured inputs usually need handmade parsing. It doesn’t even detect several common bug classes, such as integer overflows, goroutine leaks, data races, and execution timeouts. So to make it better, we built gos…
Read original ↗https://blog.trailofbits.com/2026/05/12/go-fuzzing-was-missing-half-the-toolkit.-we-forked-the-toolchain-to-fix-it.talos · tlp:amber · 5/12/2026, 10:00:54 AM
State-sponsored actors, better known as the friends you don’t want Responding to a state-sponsored threat is nothing like responding to ransomware, and the differences can make or break the outcome. Learn why your IR plan might need revisiting, and the factors you should consider. State-sponsored actors don't break in. They log in, and they use your own tools to stay invisible for months. Responding to a state-sponsored threat is nothing like respon…
Read original ↗https://blog.talosintelligence.com/state-sponsored-actors-better-known-as-the-friends-you-dont-wanthuggingface_blog · tlp:amber · 5/11/2026, 11:18:26 PM
Building Blocks for Foundation Model Training and Inference on AWS Building Blocks for Foundation Model Training and Inference on AWS Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Log In Sign Up Back to Articles Building Blocks for Foundation Model Training and Inference on AWS Enterprise Article Published May 11, 2026 Upvote 1 Keita Watanabe KeitaWatanabe Follow amazon Pavel Belevich pbelevich Follow amazon Aman Shanbhag amanshanbhag Follow amazon …
Read original ↗https://huggingface.co/blog/amazon/foundation-model-building-blocksars_security · tlp:amber · 5/11/2026, 10:28:19 PM
Linux bitten by second severe vulnerability in as many weeks Production-version patches are coming online and should be installed pronto. Linux users have been bitten by yet another vulnerability that gives containers and untrusted users the ability to gain root access, marking the second time in as many weeks that a severe threat has caught defenders off guard. The threat, known as Dirty Frag, allows low-privilege users, including those using virtual machines, to gain root…
Read original ↗https://arstechnica.com/security/2026/05/linux-bitten-by-second-severe-vulnerability-in-as-many-weeksunit42 · tlp:amber · 5/11/2026, 10:00:43 PM
Inside AD CS Escalation: Unpacking Advanced Misuse Techniques and Tools Unit 42 analyzes AD CS exploitation through template misconfigurations and shadow credential misuse while offering behavioral detection for defenders. The post Inside AD CS Escalation: Unpacking Advanced Misuse Techniques and Tools appeared first on Unit 42 . Inside AD CS Escalation: Unpacking Advanced Misuse Techniques and Tools Menu Tools ATOMs Security Consulting About Us Under Attack? Threat Researc…
Read original ↗https://unit42.paloaltonetworks.com/active-directory-certificate-services-exploitationlwn_kernel · tlp:amber · 5/11/2026, 2:35:53 PM
Stenberg: Mythos finds a curl vulnerability Daniel Stenberg has published a lengthy article on his thoughts on Anthropic's Mythos, which the company decided was too dangerous for wide public release. My personal conclusion can however not end up with anything else than that the big hype around this model so far was primarily marketing. I see no evidence that this setup finds issues to any particular higher or more advanced degree than the other tools have done before Mythos.…
Read original ↗https://lwn.net/Articles/1072325mandiant · tlp:amber · 5/11/2026, 2:00:00 PM
GTIG AI Threat Tracker: Adversaries Leverage AI for Vulnerability Exploitation, Augmented Operations, and Initial Access Executive Summary Since our February 2026 report on AI-related threat activity, Google Threat Intelligence Group (GTIG) has continued to track a maturing transition from nascent AI-enabled operations to the industrial-scale application of generative models within adversarial workflows. This report, based on insights derived from Mandiant incident response …
Read original ↗https://cloud.google.com/blog/topics/threat-intelligence/ai-vulnerability-exploitation-initial-accesslwn_kernel · tlp:amber · 5/11/2026, 1:35:31 PM
Two stable kernels with Dirty Frag fixes Greg Kroah-Hartman has released the 7.0.6 and 6.18.29 stable kernels with Hyunwoo Kim's patch for the second vulnerability ( CVE-2026-43500 ) reported with Dirty Frag and Copy Fail 2 . All users are advised to upgrade. Two stable kernels with Dirty Frag fixes [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…
Read original ↗https://lwn.net/Articles/1072311lwn_kernel · tlp:amber · 5/11/2026, 1:35:25 PM
[$] Providing 64KB base pages with 4KB kernels, two different ways Some CPU architectures are able to run with a number of different base-page sizes; using a larger size can often result in better performance at the cost of increased memory use. Other architectures are more limited. At the 2026 Linux Storage, Filesystem, Memory Management, and BPF Summit , two sessions in the memory-management track explored options for letting processes run with 64KB page sizes when the und…
Read original ↗https://lwn.net/Articles/1071484lwn_kernel · tlp:amber · 5/11/2026, 1:21:40 PM
Debian to require reproducible builds Paul Gevers has slipped an interesting bit of news into a " bits from the release team " message: Aided by the efforts of the Reproducible Builds project, we've decided it's time to say that Debian must ship reproducible packages. Since yesterday, we have enabled our migration software to block migration of new packages that can't be reproduced or existing packages (in testing) that regress in reproducibility. As Gioele Barabucci pointed…
Read original ↗https://lwn.net/Articles/1072314lwn_kernel · tlp:amber · 5/11/2026, 1:10:02 PM
Security updates for Monday Security updates have been issued by AlmaLinux (corosync, freeipmi, kernel, and kernel-rt), Debian (corosync, firefox-esr, kernel, lcms2, libpng1.6, linux-6.1, php8.2, php8.4, postorius, pyjwt, and tor), Fedora (dotnet10.0, exim, gnutls, kernel, nextcloud, nodejs22, php, proftpd, prosody, python-pulp-glue, python-requests, rclone, and SDL3_image), Mageia (firefox, nss, rootcerts, openvpn, thunderbird, and vim), Oracle (corosync, freeipmi, gstreame…
Read original ↗https://lwn.net/Articles/1072301checkpoint_research · tlp:amber · 5/11/2026, 12:49:37 PM
11th May – Threat Intelligence Report For the latest discoveries in cyber research for the week of 11th May, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES Instructure, the US education technology company behind the Canvas learning platform, has confirmed a major data breach affecting its cloud-hosted environment. Exposed data reportedly includes student and staff records and private messages, while […] The post 11th May – Threat Intelligenc…
Read original ↗https://research.checkpoint.com/2026/11th-may-threat-intelligence-reportcheckpoint_research · tlp:amber · 5/11/2026, 9:58:28 AM
The State of Ransomware – Q1 2026 Key Findings Ransomware in Q1 2026: Consolidation at Scale During the first quarter of 2026, we monitored more than 70 active data leak sites (DLS) that collectively listed 2,122 new victims. This figure represents a 12.2% decline from the Q4 2025 all-time record of 2,416 victims but remains the second-highest Q1 on record at 117% […] The post The State of Ransomware – Q1 2026 appeared first on Check Point Research . Key Finding…
Read original ↗https://research.checkpoint.com/2026/the-state-of-ransomware-q1-2026eset · tlp:amber · 5/11/2026, 8:55:00 AM
Eyes wide open: How to mitigate the security and privacy risks of smart glasses Smart glasses allow anyone to track and record the world around them. That could put your data and the privacy of those nearby at risk. Eyes wide open: How to mitigate the security and privacy risks of smart glasses Award-winning news, views, and insight from the ESET security community English Español Deutsch Português Français TIPS & ADVICE BUSINESS SECURITY ESET RESEARCH About ESET Resear…
Read original ↗https://www.welivesecurity.com/en/privacy/eyes-wide-open-mitigate-security-privacy-risks-smart-glassessnyk_blog · tlp:amber · 5/11/2026, 5:00:00 AM
TanStack Npm Packages Compromised Inside The Mini Shai Hulud Supply Chain Attack On May 11, 2026, the Mini Shai-Hulud worm compromised 84 npm package artifacts across 42 @tanstack/* packages (as well as @squawk/*, @mistralai/* packages, and others) by chaining a GitHub Actions "Pwn Request," cache poisoning, and OIDC token extraction from runner memory — producing the first npm supply chain attack with valid SLSA Build Level 3 attestations. Here's what happened, what was sto…
Read original ↗https://snyk.io/blog/tanstack-npm-packages-compromisedarxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM
Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs arXiv:2605.06669v1 Announce Type: new Abstract: Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that guardrail design entails explicit trade-offs among adversarial robustness, benign…
Read original ↗https://arxiv.org/abs/2605.06669arxiv_cs_cr · tlp:amber · 5/11/2026, 4:00:00 AM
McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware arXiv:2605.06894v1 Announce Type: new Abstract: Machine learning (ML) in real-world systems must contend with concept drift, adversarial actors, and a spectrum of potential features with varying costs and benefits. Malware naturally exhibits all of these complexities, but for the same reason, it is challenging to curate and organize data to study these factors. We present McNdroid, to…
Read original ↗https://arxiv.org/abs/2605.06894