The Semantic Trap: Do Fine-Tuned LLMs Learn Vulnerability Root Cause or Just Functional Pattern?

LLMs demonstrate promising performance in software vulnerability detection after fine-tuning. However, it remains unclear whether these gains reflect a genuine understanding of vulnerability root causes or merely an exploitation of functional patterns. In this paper, we identify a critical failur...

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...

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching

Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft. By utilizing semantic embedding vectors as cache keys, this mechanism effectively minimizes latency and redundant computation for semantically similar...

LLM-Assisted Authentication and Fraud Detection

User authentication and fraud detection face growing challenges as digital systems expand and adversaries adopt increasingly sophisticated tactics. Traditional knowledge-based authentication remains rigid, requiring exact word-for-word string matches that fail to accommodate natural human memory...

EUVD-2026-4732

AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. If AnythingLLM prior to version 1.10.0 is configured to use Qdrant as the vector database with an API key, this QdrantApiKey could be exposed in plain text to unauthenticate...

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection

Secure code review is critical at the pre-commit stage, where vulnerabilities must be caught early under tight latency and limited-context constraints. Existing SAST-based checks are noisy and often miss immature, context-dependent vulnerabilities, while standalone Large Language Models LLMs are...

Secure Intellicise Wireless Network: Agentic AI for Coverless Semantic Steganography Communication

Semantic Communication SemCom, leveraging its significant advantages in transmission efficiency and reliability, has emerged as a core technology for constructing future intellicise intelligent and concise wireless networks. However, intelligent attacks represented by semantic eavesdropping pose...

CVE-2025-66698

An issue in Semantic machines v5.4.8 allows attackers to bypass authentication via sending a crafted HTTP request to various API endpoints...

CVE-2025-66698

An issue in Semantic machines v5.4.8 allows attackers to bypass authentication via sending a crafted HTTP request to various API endpoints...

CVE-2025-66698

An issue in Semantic machines v5.4.8 allows attackers to bypass authentication via sending a crafted HTTP request to various API endpoints...

Semantic release 安全漏洞

Semantic release is a Js-based versioning and package distribution tool from the Semantic Release team. A security vulnerability exists in Semantic release version 5.4.8, which stems from the fact that sending specially crafted HTTP requests to various API endpoints can bypass authentication...

CVE-2025-66698

An issue in Semantic machines v5.4.8 allows attackers to bypass authentication via sending a crafted HTTP request to various API endpoints...

PT-2026-2487

Name of the Vulnerable Software and Affected Versions Semantic machines version 5.4.8 Description An issue allows attackers to bypass authentication by sending a crafted HTTP request to various API endpoints. The attack targets authentication mechanisms within the software. The affected API...

CVE-2025-66698

CVE-2025-66698 affects Semantic machines v5.4.8. The issue allows attackers to bypass authentication by sending a crafted HTTP request to various API endpoints. Public sources in the connected documents consistently describe the vulnerability as an authentication bypass without detailing the exac...

CVE-2025-66698

An issue in Semantic machines v5.4.8 allows attackers to bypass authentication via sending a crafted HTTP request to various API endpoints...

CVE-2022-27201

Jenkins Semantic Versioning Plugin 1.13 and earlier does not restrict execution of an controller/agent message to agents, and implements no limitations about the file path that can be parsed, allowing attackers able to control agent processes to have Jenkins parse a crafted file that uses externa...

Rethinking Secure Semantic Communications in the Age of Generative and Agentic AI: Threats and Opportunities

Semantic communication SemCom improves communication efficiency by transmitting task-relevant information instead of raw bits and is expected to be a key technology for 6G networks. Recent advances in generative AI GenAI further enhance SemCom by enabling robust semantic encoding and decoding und...

Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?

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...

SemCovert: Secure and Covert Video Transmission Via Deep Semantic-Level Hiding

Video semantic communication, praised for its transmission efficiency, still faces critical challenges related to privacy leakage. Traditional security techniques like steganography and encryption are challenging to apply since they are not inherently robust against semantic-level transformations...

Energy-Efficient Multi-LLM Reasoning for Binary-Free Zero-Day Detection in IoT Firmware

Securing Internet of Things IoT firmware remains difficult due to proprietary binaries, stripped symbols, heterogeneous architectures, and limited access to executable code. Existing analysis methods, such as static analysis, symbolic execution, and fuzzing, depend on binary visibility and...