Latest threat reports & articles

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egress arXiv:2605.20734v1 Announce Type: new Abstract: A large language model (LLM) agent that sends messages can leak data inside them. Destination allowlists and content scanners do not police whether an otherwise-benign payload is itself a covert channel: a compromised agent encodes bits in zero-width characters, homoglyphs, whitespace, base64, JavaScript Object Notation (JSON) key ordering, m…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders arXiv:2605.20759v1 Announce Type: new Abstract: Single-turn safety evaluation is a poor proxy for real fraud defense, where attackers escalate across multiple rounds. This paper evaluates fraud defenders under replay and adaptive multi-round attacks and measures when a defender refuses, not just whether it eventually refuses. On a frozen multi-round suite bu…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

GenAI-Driven Threat Detection with Microsoft Security Copilot arXiv:2605.20896v1 Announce Type: new Abstract: Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft into detection logic. This places defenders in a reactive posture, requiring constantly updated expertise across an increasingly fragmented security landscape. We introduce the Dynamic Threat Detection Agent (DTDA), an al…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Domijn: The Security of Domain Registrars and the Risk of a Domain Name Takeover arXiv:2605.20984v1 Announce Type: new Abstract: Domain names are key assets for organisation. They anchor an organisation's online presence and reputation, and serve as linking pin for web services and, e.g., email. Consequently, a malicious takeover of a domain can lead to significant damages. Organisations register domain names through so-called registrars, a type of business that plays a key …

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Verifiable Provenance and Watermarking for Generative AI: An Evidentiary Framework for International Operational Law and Domestic Courts arXiv:2605.21002v1 Announce Type: new Abstract: Generative artificial intelligence now synthesizes photorealistic imagery, audio, and video at a cost that defeats traditional forensic intuition. The legal consequences span three regimes studied so far in isolation: international operational law, domestic procedure, and product regulation. T…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

An Evidence-driven Protocol for Trustworthy CI Pipelines arXiv:2605.21089v1 Announce Type: new Abstract: Enterprise software supply chains are increasingly vulnerable to infrastructure attacks, resulting in financial and reputational damage. Ensuring the integrity and provenance of software artifacts remains a significant challenge, where re-execution of the build and tests by every consumer to guarantee provenance produces a verification bottleneck and credibility reduction…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Image Encryption via Data-Identified Discrete Chaotic Maps arXiv:2605.21118v1 Announce Type: new Abstract: In this work, we propose a data-driven image encryption framework that identifies chaotic maps directly from data using the SINDy-PI algorithm. Unlike conventional encryption schemes relying on predefined maps, our method learns the full explicit dynamics -- including cross-terms and higher-order nonlinearities -- from observational data. The validity of this approach i…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Detecting Trojaned DNNs via Spectral Regression Analysis arXiv:2605.21146v1 Announce Type: new Abstract: Modern DNNs are repeatedly fine-tuned to incorporate new data and functionality. This evolutionary workflow introduces a security risk when updated data cannot be fully trusted, as adversaries may implant Trojans during fine-tuning. We present MIST, a Trojan detection approach that analyzes how a model's internal representations change during fine-tuning. Rather than atte…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Information Leakage Envelopes arXiv:2605.21185v1 Announce Type: new Abstract: We study privacy guarantees in the framework of pointwise maximal leakage (PML) that satisfy two requirements: they are robust under post-processing and upper bound the failure probability, i.e., the probability that the information leakage exceeds a given threshold. We first examine two candidate definitions inspired by (approximate) differential privacy and show that neither one satisfies both re…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Profiling User Vulnerability to Phishing Through Psychological and Behavioral Factors arXiv:2605.21246v1 Announce Type: new Abstract: Phishing remains one of the most pervasive cybersecurity threats, shifting the focus from technological vulnerabilities to human cognitive and psychological factors. In coherence with the trend of studies on phishing to increasingly focus on human aspects and vulnerable users profiling, this study investigates the multidimensional nature of us…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Onion-Routed Multi-Circuit Key Establishment for Quantum-Resilient Sessions arXiv:2605.21349v1 Announce Type: new Abstract: Public-key primitives that today anchor session-key establishment - RSA, Diffie-Hellman, and elliptic-curve cryptography - reduce to integer factorization or discrete logarithm and are therefore vulnerable to Shor's algorithm on a sufficiently capable quantum computer. The harvest-now, decrypt-later (HNDL) threat model turns this future capability into …

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Auditing Apple's DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, and Practical Risks arXiv:2605.21378v1 Announce Type: new Abstract: Since 2016, Apple has claimed that device analytics collected to improve user experience are protected by differential privacy (DP). Apple's DifferentialPrivacy.framework is deployed across its operating systems and handles sensitive signals such as Safari domains, keyboard events, photo attributes, and health-related rep…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers arXiv:2605.21392v1 Announce Type: new Abstract: Model Context Protocol (MCP) has emerged as a standard interface for connecting LLM agents to external tools. Because MCP servers expose privileged operations such as shell execution, network access, and file-system manipulation to agent-driven invocation, implementation flaws in tool handlers can create a direct path from natural-…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs arXiv:2605.20258v1 Announce Type: cross Abstract: Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in maki…

arxiv_cs_cr · tlp:amber · 5/21/2026, 4:00:00 AM

Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions arXiv:2605.20341v1 Announce Type: cross Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive. We present HF-KCU, a method that removes a client's contribution by approximating the influence function through conjugate gradi…

lwn_kernel · tlp:amber · 5/21/2026, 2:27:57 AM

[$] LWN.net Weekly Edition for May 21, 2026 Inside this week's LWN.net Weekly Edition: Front : OpenSUSE site age restrictions; Lots of LSFMM+BPF coverage; The tenth OpenPGP email summit. Briefs : Firefox 151.0; pgBackRest funding; RIP Peter G. Neumann; Quotes; ... Announcements : Newsletters, conferences, security updates, patches, and more.

chainalysis · tlp:amber · 5/20/2026, 11:36:03 PM

OFAC Sanctions Sinaloa Cartel Fentanyl Trafficking and Crypto Laundering Network Summary The Department of the Treasury’s Office of Foreign Assets Control (OFAC) sanctioned more than a dozen individuals and entities… The post OFAC Sanctions Sinaloa Cartel Fentanyl Trafficking and Crypto Laundering Network appeared first on Chainalysis . OFAC Sanctions Fentanyl Trafficking and Crypto Laundering Network Chainalysis Products Crypto Investigations Investigations Solutions…

ars_security · tlp:amber · 5/20/2026, 7:10:36 PM

Google publishes exploit code threatening millions of Chromium users Google publishes exploit code before patch, reported 29 months earlier, is fixed. Google on Wednesday published exploit code for an unfixed vulnerability in its Chromium browser codebase that threatens millions of people using Chrome, Microsoft Edge, and virtually all other Chromium-based browsers. The proof-of-concept code exploits the Browser Fetch programming interface, a standard that allows long video…

microsoft_mstic · tlp:amber · 5/20/2026, 5:48:44 PM

Mini Shai Hulud: Compromised @antv npm packages enable CI/CD credential theft Compromised @antv npm packages deploy the Mini Shai-Hulud payload to steal CI/CD secrets from Linux-based automation environments. The malware executes during npm install and targets credentials across GitHub, AWS, Kubernetes, Vault, npm, and 1Password platforms. The post Mini Shai Hulud: Compromised @antv npm packages enable CI/CD credential theft appeared first on Microsoft Security Blog . Micro…

microsoft_mstic · tlp:amber · 5/20/2026, 4:00:00 PM

Securing the gaming culture of cultures Read about the unique challenges and rewards of securing gaming platforms and how to better protect gaming communities. The post Securing the gaming culture of cultures appeared first on Microsoft Security Blog . The Deputy CISO blog series is where  Microsoft  Deputy Chief Information Security Officers  (CISOs) share their thoughts on what is most important in their respective domains. In this series, you will get prac…

microsoft_mstic · tlp:amber · 5/20/2026, 3:00:00 PM

Introducing RAMPART and Clarity: Open source tools to bring safety into Agent development workflow The AI systems shipping inside enterprises today are fundamentally different from the ones we were building even two years ago, because they have moved well past answering questions and into accessing your email, retrieving records from your CRM, writing and executing code, and taking actions on your behalf across dozens of connected systems. The post Introducing RAMPART and Cl…

lwn_kernel · tlp:amber · 5/20/2026, 1:14:51 PM

[$] What is to be done about MGLRU? "Reclaim" is the task of finding memory that can be taken away from its current user and put to better uses within the system; it is a core part of the memory-management picture. The addition of the multi-generational LRU (MGLRU) was meant to provide a better reclaim implementation than the "traditional LRU" that preceded it, but MGLRU has complicated the situation instead. No fewer than three memory-management-track sessions at the 2026 L…

lwn_kernel · tlp:amber · 5/20/2026, 1:04:17 PM

Security updates for Wednesday Security updates have been issued by AlmaLinux (kernel, libpng, nginx, nginx:1.24, ruby, and ruby:3.3), Debian (gnutls28 and linux-6.1), Fedora (dnsmasq, kernel, keylime-agent-rust, perl-Net-CIDR-Lite, python-pysam, python-urllib3, rust-cargo-vendor-filterer, rust-ingredients, rust-oo7-cli, rust-rpki, rust-sevctl, and rust-tealdeer), Mageia (bind), Oracle (bind, giflib, gimp:2.8, kernel, libpng, rsync, ruby, and vim), Slackware (haveged and moz…

cisa_alerts · tlp:amber · 5/20/2026, 12:00:00 PM

CISA Adds Seven Known Exploited Vulnerabilities to Catalog CISA has added seven new vulnerabilities to its Known Exploited Vulnerabilities (KEV) Catalog , based on evidence of active exploitation. CVE-2008-4250 Microsoft Windows Buffer Overflow Vulnerability CVE-2009-1537 Microsoft DirectX NULL Byte Overwrite Vulnerability CVE-2009-3459 Adobe Acrobat and Reader Heap-Based Buffer Overflow Vulnerability CVE-2010-0249 Microsoft Internet Explorer Use-After-Free Vulnerability CVE…

chainalysis · tlp:amber · 5/20/2026, 11:55:18 AM

How Blockchain Intelligence Uncovered a Million-Euro Bitcoin Ordinals Tax Fraud Scheme Summary Criminals are increasingly turning to novel digital asset classes, like Bitcoin Ordinals and BRC-20 tokens, to generate and conceal… The post How Blockchain Intelligence Uncovered a Million-Euro Bitcoin Ordinals Tax Fraud Scheme appeared first on Chainalysis . How Blockchain Intelligence Uncovered a Bitcoin Ordinals Scheme Chainalysis Products Crypto Investigations Investiga…

lwn_kernel · tlp:amber · 5/20/2026, 11:00:15 AM

[$] The tenth OpenPGP email summit The OpenPGP Email Summit is an annual meeting for those who work on encrypted email and related topics. The tenth installment of this meeting took place in March 2026 and the minutes have now been published. As usual, a wide range of topics were discussed. Highlights included support for post-quantum cryptography (PQC) with multiple actors planning rollouts within this year, a promising new approach for making email signatures ubiquitous wi…

unit42 · tlp:amber · 5/20/2026, 10:00:46 AM

Tracking TamperedChef Clusters via Certificate and Code Reuse Unit 42 analyzes TamperedChef malware clusters that use trojanized productivity apps and malvertising to deliver stealthy payloads to targets. The post Tracking TamperedChef Clusters via Certificate and Code Reuse appeared first on Unit 42 . Tracking TamperedChef Clusters via Certificate and Code Reuse Menu Tools ATOMs Security Consulting About Us Under Attack? Threat Research Center Threat Research Malware Malwa…

eset · tlp:amber · 5/20/2026, 8:40:00 AM

Webworm: New burrowing techniques ESET researchers describe new tools and techniques that the Webworm APT group recently added to its arsenal Webworm: New burrowing techniques 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 Ukraine crisis – Digital security resource cent…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks arXiv:2605.18919v1 Announce Type: new Abstract: Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from inefficient crossover operations that destroy adversarial properties through discrete interpolation. We introduce Mode Connectivity Evolutionary Attack (MoCo-EA), which replaces traditional cro…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

Quantum Machine Learning for Cyber-Physical Anomaly Detection in Unmanned Aerial Vehicles: A Leakage-Free Evaluation with Proxy-Audited Feature Sets arXiv:2605.19233v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) are cyber-physical systems whose attack surface spans networked avionics and on-board sensor fusion: a compromised GPS or battery module can mimic a benign mission segment and evade naive anomaly detectors. We present a leakage-free evaluation of qua…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

Devilray: A Systematic Adversarial Model Revealing Blind Spots in Fake Base Station Detection arXiv:2605.19232v1 Announce Type: new Abstract: Fake Base Station (FBS) detection has been a critical focus of cellular security research for over two decades. However, significant financial and regulatory barriers to accessing commercial FBS (C-FBS) devices have limited direct visibility into real-world operations, forcing detection systems to be designed and evaluated around self-…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models arXiv:2605.19227v1 Announce Type: new Abstract: Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new vulnerabilities. In particular, we are the first to show…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

On the Geometric Limits of Transformer Defenses against Obfuscation Attacks: Latent Embedding Collapse & Performance Robustness Gap arXiv:2605.19159v1 Announce Type: new Abstract: Prompt injection attacks pose significant risks to language model safety, yet existing defenses are typically evaluated using classification performance. We show that high detection performance does not imply representational robustness. Specifically, multi-operator obfuscated prompts (combining ho…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks arXiv:2605.19147v1 Announce Type: new Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM rewriting as a proactive defense agai…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

Structural Analysis of Cryptographic Sequences using Stringology-Based Fingerprinting arXiv:2605.19123v1 Announce Type: new Abstract: Cryptographic primitives such as stream ciphers,Pseudorandom Number Generators (PRNGs), and block cipher modes produce sequences that are designed to be statistically indistinguishable from random data. As a result, the traditional evaluation techniques therefore rely primarily on statistical randomness tests to assess the quality of generated…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

Agent Security is a Systems Problem arXiv:2605.18991v1 Announce Type: new Abstract: We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness (the dominant viewpoint in the community) are insufficient on their own. Instead, we must complement existing efforts wi…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks arXiv:2605.18988v1 Announce Type: new Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary attack surface. Empirical observations indicate that adversaries employ progressive, cross-modal perturbations that evade turn-specific guardrails by distributing malicious intent across longitudinal conv…

arxiv_cs_cr · tlp:amber · 5/20/2026, 4:00:00 AM

OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences arXiv:2605.18930v1 Announce Type: new Abstract: Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access or explicit malicious content, making them detectable by advanced safety filters. This leaves a subtler attack sur…