Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection

SMS-based phishing smishing attacks have surged, yet training effective on-device detectors requires labelled threat data that quickly becomes outdated. To deal with this issue, we present Agentic Knowledge Distillation, which consists of a powerful LLM acts as an autonomous teacher that fine-tun...

Security Assessment of Intel TDX with Support for Live Migration

In the second and third quarters of 2025, Google collaborated with Intel to conduct a security assessment of Intel Trust Domain Extensions TDX, extending Google's previous review and covering major changes since Intel TDX Module 1.0 - namely support for Live Migration and Trusted Domain TD...

VulReaD: Knowledge-Graph-Guided Software Vulnerability Reasoning and Detection

Software vulnerability detection SVD is a critical challenge in modern systems. Large language models LLMs offer natural-language explanations alongside predictions, but most work focuses on binary evaluation, and explanations often lack semantic consistency with Common Weakness Enumeration CWE...

SAFuzz: Semantic-Guided Adaptive Fuzzing for LLM-Generated Code

While AI-coding assistants accelerate software development, current testing frameworks struggle to keep pace with the resulting volume of AI-generated code. Traditional fuzzing techniques often allocate resources uniformly and lack semantic awareness of algorithmic vulnerability patterns, leading...

LLM-FS: Zero-Shot Feature Selection for Effective and Interpretable Malware Detection

Feature selection FS remains essential for building accurate and interpretable detection models, particularly in high-dimensional malware datasets. Conventional FS methods such as Extra Trees, Variance Threshold, Tree-based models, Chi-Squared tests, ANOVA, Random Selection, and Sequential...

Protecting Context and Prompts: Deterministic Security for Non-Deterministic AI

Large Language Model LLM applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated context--that provide cryptographically verifiable provenance acros...

⚡ Weekly Recap: AI Skill Malware, 31Tbps DDoS, Notepad++ Hack, LLM Backdoors and More

Cyber threats are no longer coming from just malware or exploits. They’re showing up inside the tools, platforms, and ecosystems organizations use every day. As companies connect AI, cloud apps, developer tools, and communication systems, attackers are following those same paths. A clear pattern...

Exploring Semantic Labeling Strategies for Third-Party Cybersecurity Risk Assessment Questionnaires

Third-Party Risk Assessment TPRA is a core cybersecurity practice for evaluating suppliers against standards such as ISO/IEC 27001 and NIST. TPRA questionnaires are typically drawn from large repositories of security and compliance questions, yet tailoring assessments to organizational needs...

Rethinking Latency Denial-Of-Service: Attacking the LLM Serving Framework, Not the Model

Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks. Recently, a growing body of research has focused on algorithmic...

KRONE: Hierarchical and Modular Log Anomaly Detection

Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when they are stored as flat sequences. As a result, state-of-the-art methods risk missing true dependencies...

Persistent Human Feedback, LLMs, and Static Analyzers for Secure Code Generation and Vulnerability Detection

Existing literature heavily relies on static analysis tools to evaluate LLMs for secure code generation and vulnerability detection. We reviewed 1,080 LLM-generated code samples, built a human-validated ground-truth, and compared the outputs of two widely used static security tools, CodeQL and...

Detecting backdoored language models at scale

Today, we are releasing new research on detecting backdoors in open-weight language models. Our research highlights several key properties of language model backdoors, laying the groundwork for a practical scanner designed to detect backdoored models at scale and improve overall trust in AI...

CVE-2026-22778 vLLM leaks a heap address when PIL throws an error

vLLM is an inference and serving engine for large language models LLMs. From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guess...

CVE-2026-0599

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

CVE-2026-0599

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

CVE-2026-0599 Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

CVE-2026-0599 Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

EUVD-2026-5137

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

PT-2026-5654

Name of the Vulnerable Software and Affected Versions huggingface/text-generation-inference version 3.3.6 huggingface/text-generation-inference versions prior to 3.3.7 Description A flaw exists in huggingface/text-generation-inference that allows unauthenticated remote attackers to cause a...

Text Generation Inference 资源管理错误漏洞

Text Generation Inference is a Rust, Python, and gRPC server developed by Hugging Face for text generation inference. Version 3.3.6 of Text Generation Inference contains a resource management vulnerability. This vulnerability stems from the unlimited acquisition of external images during input...