One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders Via Hubness

The hubness problem, in which hub embeddings are close to many unrelated examples, occurs often in high-dimensional embedding spaces and may pose a practical threat for purposes such as information retrieval and automatic evaluation metrics. In particular, since cross-modal similarity between tex...

AsmRAG: LLM-Driven Malware Detection by Retrieving Functionally Similar Assembly Code

Deep learning malware detectors achieve high classification accuracy but suffer from severe interpretability limitations, typically returning probabilistic verdicts that lack forensic context. We introduce AsmRAG, a framework performing malware analysis through Assembly-Level Retrieval-Augmented...

FixV2W: Correcting Invalid CVE-CWE Mappings with Knowledge Graph Embeddings

Accurate mapping between Common Vulnerabilities and Exposures CVE and Common Weakness Enumeration CWE entries is critical for effective vulnerability management and risk assessment. However, public databases, such as the National Vulnerability Database NVD, suffer from inconsistent and incomplete...

VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database

Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public repositories, such as the National Vulnerability Database and CVE details, are regularly updated, but predominantly utilize relational data models...

Security Bulletin: Vulnerabilities in llama_index_core bundled with IBM Fusion, IBM Fusion HCI and Content-Aware Storage.

Summary IBM Fusion, IBM Fusion HCI and Content-Aware Storage includes llamaindexcore which could allow Denial of Service DoS, steal proprietary models, poison cached embeddings, conduct symlink attacks. CVE-2025-5472, CVE-2024-12911, CVE-2024-12704, CVE-2025-5302, CVE-2025-7647. Vulnerability...

PT-2026-28324

Name of the Vulnerable Software and Affected Versions Spring AI versions 1.0.0 through 1.0.4 and 1.1.0 through 1.1.3 Description Spring AI's SimpleVectorStore component contains a SpEL injection flaw. This occurs when user-provided input is used as a filter expression key. A malicious actor can...

SUSE CVE-2026-30859

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to other tenants, including API keys, mod...

CVE-2026-30859

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to other tenants, including API keys, mod...

CVE-2026-30859

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to other tenants, including API keys, mod...

CVE-2026-30859

WeKnora prior to version 0.2.12 suffers broken access control in the database query tool, allowing any authenticated tenant to read data from other tenants (models, messages, embeddings) including API keys and model configurations due to failure to enforce tenant isolation on critical tables. The...

CVE-2026-30859 WeKnora: Broken Access Control - Cross-Tenant Data Exposure

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to other tenants, including API keys, mod...

CVE-2026-30859 WeKnora: Broken Access Control - Cross-Tenant Data Exposure

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.12, a broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to other tenants, including API keys, mod...

WeKnora has Broken Access Control - Cross-Tenant Data Exposure

Summary A broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to other tenants, including API keys, model configurations, and private messages. The application fails to enforce tenant isolation on critical tables models,...

GHSA-2F4C-VRJQ-RCGV WeKnora has Broken Access Control - Cross-Tenant Data Exposure

Summary A broken access control vulnerability in the database query tool allows any authenticated tenant to read sensitive data belonging to other tenants, including API keys, model configurations, and private messages. The application fails to enforce tenant isolation on critical tables models,...

PT-2026-23802

Name of the Vulnerable Software and Affected Versions WeKnora versions prior to 0.2.12 Description WeKnora is a framework for deep document understanding and semantic retrieval. A broken access control issue in the database query tool allows any authenticated tenant to read sensitive data belongi...

Predicting Known Vulnerabilities from Attack Descriptions Using Sentence Transformers

Modern infrastructures rely on software systems that remain vulnerable to cyberattacks. These attacks frequently exploit vulnerabilities documented in repositories such as MITRE's Common Vulnerabilities and Exposures CVE. However, Cyber Threat Intelligence resources, including MITRE ATT&CK and CV...

PT-2026-41200

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.8.0 Description The endpoint "/api/v1/memories/ef" is accessible without authentication and executes the function request.app.state.EMBEDDING FUNCTION. This allows unauthenticated users to trigger embedding...

Semantic-Aware Advanced Persistent Threat Detection Using Autoencoders on LLM-Encoded System Logs

Advanced Persistent Threats APTs are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit "low-and-slow" behavior, traditional statistical methods and...

SecureSplit: Mitigating Backdoor Attacks in Split Learning

Split Learning SL offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks, in which malicious clients subtly alter their embeddings to...

Out-of-bounds Write

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Out-of-bounds Write via the todense function in the Completions API endpoint when processing user-supplied prompt embeddings. An attacker can achiev...