Weekly Threat Intelligence Summary

Top 10 General Cyber Threats

Generated 2026-01-05T05:00:04.821690+00:00

1. GrayBravo’s CastleLoader Activity Clusters Target Multiple Industries (www.recordedfuture.com, 2025-12-09T00:00:00)
   Score: 11.465
   Note: The analysis cut-off date for this report was November 10, 2025 Executive Summary Insikt Group continues to monitor GrayBravo (formerly tracked as TAG-150), a technically sophisticated and rapidly evolving threat actor first identified in September 2025. GrayBravo demonstrates strong adaptability, responsiveness to public exposure, and operates a large-scale, multi-layered infrastructure. Recent analysis of GrayBravo’s ecosystem uncovered four distinct activity clusters leveraging the grou
2. Malware in 2025 spread far beyond Windows PCs (www.malwarebytes.com, 2025-12-29T11:48:34)
   Score: 7.081
   Windows isn’t the only target anymore. In 2025, malware increasingly targeted Android, macOS, and multiple platforms at once.
3. Critical React2Shell Vulnerability Under Active Exploitation by Chinese Threat Actors (www.recordedfuture.com, 2025-12-08T00:00:00)
   Score: 6.999
   A critical vulnerability in React Server Components is allegedly being actively exploited by multiple Chinese threat actors, Recorded Future recommends organizations patch their systems immediately.
4. December 2025 Patch Tuesday: One Critical Zero-Day, Two Publicly Disclosed Vulnerabilities Among 57 CVEs (www.crowdstrike.com, 2025-12-09T06:00:00)
   Score: 6.207
5. How AI made scams more convincing in 2025 (www.malwarebytes.com, 2026-01-02T10:16:04)
   Score: 5.737
   Several AI-related stories in 2025 highlighted how quickly AI systems can move beyond meaningful human control.
6. CISA warns ASUS Live Update backdoor is still exploitable, seven years on (www.malwarebytes.com, 2025-12-19T13:56:36)
   Score: 5.429
   Seven years after the original attack, CISA has added the ASUS Live Update backdoor to its Known Exploited Vulnerabilities catalog.
7. In 2025, age checks started locking people out of the internet (www.malwarebytes.com, 2025-12-31T10:49:04)
   Score: 5.407
   Lawmakers enforced age checks, websites blocked entire countries, and users turned to VPNs to get around them.
8. 2025 exposed the risks we ignored while rushing AI (www.malwarebytes.com, 2025-12-30T10:02:11)
   Score: 5.235
   We explore how the rapid rise of Artificial Intelligence (AI) is putting users at risk.
9. November 2025 CVE Landscape: 10 Critical Vulnerabilities Show 69% Drop from October (www.recordedfuture.com, 2025-12-09T00:00:00)
   Score: 5.165
   November 2025 CVE landscape: 10 exploited critical vulnerabilities, a 69% drop from October, and why Fortinet and Samsung flaws need urgent patching.
10. Inside a purchase order PDF phishing campaign (www.malwarebytes.com, 2025-12-17T13:38:00)
    Score: 5.093
    A “purchase order” PDF blocked by Malwarebytes led to a credential-harvesting phishing site. So we analyzed the attack and where the data went next.

Top 10 AI / LLM-Related Threats

Generated 2026-01-05T06:00:15.632121+00:00

1. Overlooked Safety Vulnerability in LLMs: Malicious Intelligent Optimization Algorithm Request and its Jailbreak (arxiv.org, 2026-01-05T05:00:00)
   Score: 20.79
   arXiv:2601.00213v1 Announce Type: new
   Abstract: The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and agent-based applications, their vulnerabilities in automated algorithm design remain underexplored. To fill this gap, this study investigates this overlooked safety vulnerability, with a particular focus on intelligent
2. Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems (arxiv.org, 2026-01-05T05:00:00)
   Score: 17.79
   arXiv:2601.00274v1 Announce Type: new
   Abstract: Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a key technique for enhancing Large Language Models (LLMs) with proprietary Knowledge Graphs (KGs) in knowledge-intensive applications. As these KGs often represent an organization's highly valuable intellectual property (IP), they face a significant risk of theft for private use. In this scenario, attackers operate in isolated environments. This private-use threat renders passive
3. One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models (arxiv.org, 2026-01-05T05:00:00)
   Score: 17.79
   arXiv:2505.07167v3 Announce Type: replace
   Abstract: Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the models into generating harmful responses despite safety alignment. Recent studies have shown that current safety-aligned LLMs undergo shallow safety alignment. In this work, we conduct an in-depth investigation
4. Red Teaming Large Reasoning Models (arxiv.org, 2026-01-05T05:00:00)
   Score: 17.79
   arXiv:2512.00412v2 Announce Type: replace
   Abstract: Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies, which are not fully captured by existing evaluation methods. To address this gap, we propose RT-LRM, a unified benchmark desi
5. From Description to Score: Can LLMs Quantify Vulnerabilities? (arxiv.org, 2026-01-05T05:00:00)
   Score: 17.79
   arXiv:2512.06781v2 Announce Type: replace
   Abstract: Manual vulnerability scoring, such as assigning Common Vulnerability Scoring System (CVSS) scores, is a resource-intensive process that is often influenced by subjective interpretation. This study investigates the potential of general-purpose large language models (LLMs), namely ChatGPT, Llama, Grok, DeepSeek, and Gemini, to automate this process by analyzing over 31{,}000 recent Common Vulnerabilities and Exposures (CVE) entries. The results
6. Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments (arxiv.org, 2026-01-05T05:00:00)
   Score: 17.79
   arXiv:2511.13788v2 Announce Type: replace-cross
   Abstract: Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can systematically jailbreak smaller ones – eliciting harmful or restricted behavior despite alignment safeguards. Using standardized adversarial tasks from JailbreakBench, we simulate over 6,000 multi-turn
7. Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback (arxiv.org, 2026-01-05T05:00:00)
   Score: 16.79
   arXiv:2601.00509v1 Announce Type: new
   Abstract: Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs benefit substantially from structured feedback, static analysis, retrieval augmentation, and execution-based refinement. We propose a retrieval-augmented, multi-tool repair workflow in which a single code-generating LLM iteratively refines its outputs using compiler diagnost
8. Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools? (arxiv.org, 2026-01-05T05:00:00)
   Score: 14.79
   arXiv:2601.00559v1 Announce Type: new
   Abstract: Smart home IoT platforms such as openHAB rely on Trigger Action Condition (TAC) rules to automate device behavior, but the interplay among these rules can give rise to interaction threats, unintended or unsafe behaviors emerging from implicit dependencies, conflicting triggers, or overlapping conditions. Identifying these threats requires semantic understanding and structural reasoning that traditionally depend on symbolic, constraint-driven stati
9. Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems (arxiv.org, 2026-01-05T05:00:00)
   Score: 14.79
   arXiv:2601.00566v1 Announce Type: new
   Abstract: Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing update costs by introducing trainable low-rank matrices. However, when integrated with frameworks like FedIT, LoRA introduces a critical vulnerability: clients submit $A$ and $B$ matrices separately, while only their product $AB$ determines the model update, yet this composite is never directly verified
10. PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration (arxiv.org, 2026-01-05T05:00:00)
    Score: 13.79
    arXiv:2512.08809v2 Announce Type: replace
    Abstract: With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior methods, relying on differential privacy within device-cloud collaboration frameworks, struggle to balance privacy and utility, exposing users to inference attacks or degrading fine-tuning performance. To addre
11. Optimizing LLM inference on Amazon SageMaker AI with BentoML’s LLM- Optimizer (aws.amazon.com, 2025-12-24T17:17:44)
    Score: 12.955
    In this post, we demonstrate how to optimize large language model (LLM) inference on Amazon SageMaker AI using BentoML's LLM-Optimizer to systematically identify the best serving configurations for your workload.
12. Deploy Mistral AI’s Voxtral on Amazon SageMaker AI (aws.amazon.com, 2025-12-22T18:32:19)
    Score: 12.491
    In this post, we demonstrate hosting Voxtral models on Amazon SageMaker AI endpoints using vLLM and the Bring Your Own Container (BYOC) approach. vLLM is a high-performance library for serving large language models (LLMs) that features paged attention for improved memory management and tensor parallelism for distributing models across multiple GPUs.
13. Large Empirical Case Study: Go-Explore adapted for AI Red Team Testing (arxiv.org, 2026-01-05T05:00:00)
    Score: 12.49
    arXiv:2601.00042v1 Announce Type: new
    Abstract: Production LLM agents with tool-using capabilities require security testing despite their safety training. We adapt Go-Explore to evaluate GPT-4o-mini across 28 experimental runs spanning six research questions. We find that random-seed variance dominates algorithmic parameters, yielding an 8x spread in outcomes; single-seed comparisons are unreliable, while multi-seed averaging materially reduces variance in our setup. Reward shaping consistently
14. LLM-Powered Analysis of IoT User Reviews: Tracking and Ranking Security and Privacy Concerns (arxiv.org, 2026-01-05T05:00:00)
    Score: 12.49
    arXiv:2601.00372v1 Announce Type: new
    Abstract: Being able to understand the security and privacy (S&P) concerns of IoT users brings benefits to both developers and users. To learn about users' views, we examine Amazon IoT reviews – one of the biggest IoT markets. This work presents a state-of-the-art methodology to identify and categorize reviews in which users express S&P concerns. We developed an automated pipeline by fine-tuning GPT-3.5-Turbo to build two models: the Classifier
15. Cyberscurity Threats and Defense Mechanisms in IoT network (arxiv.org, 2026-01-05T05:00:00)
    Score: 11.99
    arXiv:2601.00556v1 Announce Type: new
    Abstract: The rapid proliferation of Internet of Things (IoT) technologies, projected to exceed 30 billion interconnected devices by 2030, has significantly escalated the complexity of cybersecurity challenges. This survey aims to provide a comprehensive analysis of vulnerabilities, threats, and defense mechanisms, specifically focusing on the integration of network and application layers within real-time monitoring and decision-making systems. Employing an
16. The Trojan in the Vocabulary: Stealthy Sabotage of LLM Composition (arxiv.org, 2026-01-05T05:00:00)
    Score: 11.49
    arXiv:2601.00065v1 Announce Type: cross
    Abstract: The open-weight LLM ecosystem is increasingly defined by model composition techniques (such as weight merging, speculative decoding, and vocabulary expansion) that remix capabilities from diverse sources. A critical prerequisite for applying these methods across different model families is tokenizer transplant, which aligns incompatible vocabularies to a shared embedding space. We demonstrate that this essential interoperability step introduces
17. PatchBlock: A Lightweight Defense Against Adversarial Patches for Embedded EdgeAI Devices (arxiv.org, 2026-01-05T05:00:00)
    Score: 9.49
    arXiv:2601.00367v1 Announce Type: new
    Abstract: Adversarial attacks pose a significant challenge to the reliable deployment of machine learning models in EdgeAI applications, such as autonomous driving and surveillance, which rely on resource-constrained devices for real-time inference. Among these, patch-based adversarial attacks, where small malicious patches (e.g., stickers) are applied to objects, can deceive neural networks into making incorrect predictions with potentially severe conseque
18. Towards Understanding and Characterizing Vulnerabilities in Intelligent Connected Vehicles through Real-World Exploits (arxiv.org, 2026-01-05T05:00:00)
    Score: 9.49
    arXiv:2601.00627v1 Announce Type: new
    Abstract: Intelligent Connected Vehicles (ICVs) are a core component of modern transportation systems, and their security is crucial as it directly relates to user safety. Despite prior research, most existing studies focus only on specific sub-components of ICVs due to their inherent complexity. As a result, there is a lack of systematic understanding of ICV vulnerabilities. Moreover, much of the current literature relies on human subjective analysis, such
19. The CoinAlg Bind: Profitability-Fairness Tradeoffs in Collective Investment Algorithms (arxiv.org, 2026-01-05T05:00:00)
    Score: 9.49
    arXiv:2601.00523v1 Announce Type: cross
    Abstract: Collective Investment Algorithms (CoinAlgs) are increasingly popular systems that deploy shared trading strategies for investor communities. Their goal is to democratize sophisticated — often AI-based — investing tools. We identify and demonstrate a fundamental profitability-fairness tradeoff in CoinAlgs that we call the CoinAlg Bind: CoinAlgs cannot ensure economic fairness without losing profit to arbitrage. We present a formal model of Coin
20. Fusion of Machine Learning and Blockchain-based Privacy-Preserving Approach for Health Care Data in the Internet of Things (arxiv.org, 2026-01-05T05:00:00)
    Score: 9.49
    arXiv:2510.19026v3 Announce Type: replace
    Abstract: In recent years, the rapid integration of Internet of Things (IoT) devices into the healthcare sector has brought about revolutionary advancements in patient care and data management. While these technological innovations hold immense promise, they concurrently raise critical security concerns, particularly in safeguarding medical data against potential cyber threats. The sensitive nature of health-related information requires robust measures
21. Introducing Visa Intelligent Commerce on AWS: Enabling agentic commerce with Amazon Bedrock AgentCore (aws.amazon.com, 2025-12-23T16:45:47)
    Score: 9.411
    In this post, we explore how AWS and Visa are partnering to enable agentic commerce through Visa Intelligent Commerce using Amazon Bedrock AgentCore. We demonstrate how autonomous AI agents can transform fragmented shopping and travel experiences into seamless, end-to-end workflows—from discovery and comparison to secure payment authorization—all driven by natural language.
22. Build a multimodal generative AI assistant for root cause diagnosis in predictive maintenance using Amazon Bedrock (aws.amazon.com, 2025-12-22T18:21:28)
    Score: 9.189
    In this post, we demonstrate how to implement a predictive maintenance solution using Foundation Models (FMs) on Amazon Bedrock, with a case study of Amazon's manufacturing equipment within their fulfillment centers. The solution is highly adaptable and can be customized for other industries, including oil and gas, logistics, manufacturing, and healthcare.
23. Migrate MLflow tracking servers to Amazon SageMaker AI with serverless MLflow (aws.amazon.com, 2025-12-29T17:29:27)
    Score: 8.847
    This post shows you how to migrate your self-managed MLflow tracking server to a MLflow App – a serverless tracking server on SageMaker AI that automatically scales resources based on demand while removing server patching and storage management tasks at no cost. Learn how to use the MLflow Export Import tool to transfer your experiments, runs, models, and other MLflow resources, including instructions to validate your migration's success.
24. Improving Router Security using BERT (arxiv.org, 2026-01-05T05:00:00)
    Score: 8.79
    arXiv:2601.00783v1 Announce Type: new
    Abstract: Previous work on home router security has shown that using system calls to train a transformer-based language model built on a BERT-style encoder using contrastive learning is effective in detecting several types of malware, but the performance remains limited at low false positive rates. In this work, we demonstrate that using a high-fidelity eBPF-based system call sensor, together with contrastive augmented learning (which introduces controlled
25. Mage: Cracking Elliptic Curve Cryptography with Cross-Axis Transformers (arxiv.org, 2026-01-05T05:00:00)
    Score: 8.79
    arXiv:2512.12483v3 Announce Type: replace
    Abstract: With the advent of machine learning and quantum computing, the 21st century has gone from a place of relative algorithmic security, to one of speculative unease and possibly, cyber catastrophe.
    Modern algorithms like Elliptic Curve Cryptography (ECC) are the bastion of current cryptographic security protocols that form the backbone of consumer protection ranging from Hypertext Transfer Protocol Secure (HTTPS) in the modern internet browser,

Auto-generated 2026-01-05