LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks

Dynamic Symbolic Execution DSE is a key technique in program analysis, widely used in software testing, vulnerability discovery, and formal verification. In distributed AI systems, DSE plays a crucial role in identifying hard-to-detect bugs, especially those arising from complex network...

Enhancing Phishing Detection in Financial Systems through NLP

The threat of phishing attacks in financial systems is continuously growing. Therefore, protecting sensitive information from unauthorized access is paramount. This paper discusses the critical need for robust email phishing detection. Several existing methods, including blacklists and whitelists...

SAMEP: a Secure Protocol for Persistent Context Sharing across AI Agents

Current AI agent architectures suffer from ephemeral memory limitations, preventing effective collaboration and knowledge sharing across sessions and agent boundaries. We introduce SAMEP Secure Agent Memory Exchange Protocol, a novel framework that enables persistent, secure, and semantically...

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

The proliferation of Low-Rank Adaptation LoRA models has democratized personalized text-to-image generation, enabling users to share lightweight models e.g., personal portraits on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs c...

Diffusion-Based Task-Oriented Semantic Communications with Model Inversion Attack

Semantic communication has emerged as a promising neural network-based system design for 6G networks. Task-oriented semantic communication is a novel paradigm whose core goal is to efficiently complete specific tasks by transmitting semantic information, optimizing communication efficiency and ta...

RISC Zero Ethereum 安全漏洞

RISC Zero Ethereum is a computing platform open-sourced by RISC Zero. A security vulnerability exists in RISC Zero Ethereum versions prior to 2.1.1 and 2.2.0, which stems from the Steel.validateCommitment function returning true for a commitment with a summary value of zero, which could lead to a...

PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty

Large Language Models LLMs are widely used in sensitive domains, including healthcare, finance, and legal services, raising concerns about potential private information leaks during inference. Privacy extraction attacks, such as jailbreaking, expose vulnerabilities in LLMs by crafting inputs that...

GHSA-9623-MJ7J-P9V4 Quarkus potentially leaks data when duplicating a duplicated context

Impact Vert.x 4.5.12 has changed the semantics of the duplication of duplicated context. Duplicated context is an object used to propagate data through a processing synchronous or asynchronous. Each "transaction" or "processing" runs on its own isolated duplicated context. Initially, duplicating ...

Multi-Domain Anomaly Detection in a 5G Network

With the advent of 5G, mobile networks are becoming more dynamic and will therefore present a wider attack surface. To secure these new systems, we propose a multi-domain anomaly detection method that is distinguished by the study of traffic correlation on three dimensions: temporal by analyzing...

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity

Large Language Models LLMs have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many suffer from computational expense, high token usage, or...

Leveraging GPT-4 for Vulnerability-Witnessing Unit Test Generation

In the life-cycle of software development, testing plays a crucial role in quality assurance. Proper testing not only increases code coverage and prevents regressions but it can also ensure that any potential vulnerabilities in the software are identified and effectively fixed. However, creating...

Semantic Preprocessing for LLM-Based Malware Analysis

In a context of malware analysis, numerous approaches rely on Artificial Intelligence to handle a large volume of data. However, these techniques focus on data view images, sequences and not on an expert's view. Noticing this issue, we propose a preprocessing that focuses on expert knowledge to...

OSI Stack Redesign for Quantum Networks: Requirements, Technologies, Challenges, and Future Directions

Quantum communication is poised to become a foundational element of next-generation networking, offering transformative capabilities in security, entanglement-based connectivity, and computational offloading. However, the classical OSI model-designed for deterministic and error-tolerant...

PhishDebate: an LLM-Based Multi-Agent Framework for Phishing Website Detection

Phishing websites continue to pose a significant cybersecurity threat, often leveraging deceptive structures, brand impersonation, and social engineering tactics to evade detection. While recent advances in large language models LLMs have enabled improved phishing detection through contextual...

CipherMind: the Longest Codebook in the World

In recent years, the widespread application of large language models has inspired us to consider using inference for communication encryption. We therefore propose CipherMind, which utilizes intermediate results from deterministic fine-tuning of large model inferences as transmission content. The...

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis

The integration of open-source third-party library dependencies in Java development introduces significant security risks when these libraries contain known vulnerabilities. Existing Software Composition Analysis SCA tools struggle to effectively detect vulnerable API usage from these libraries d...

Analyzing PDFs like Binaries: Adversarially Robust PDF Malware Analysis Via Intermediate Representation and Language Model

Malicious PDF files have emerged as a persistent threat and become a popular attack vector in web-based attacks. While machine learning-based PDF malware classifiers have shown promise, these classifiers are often susceptible to adversarial attacks, undermining their reliability. To address this...

Semantic-Aware Parsing for Security Logs

Security analysts struggle to quickly and efficiently query and correlate log data due to the heterogeneity and lack of structure in real-world logs. Existing AI-based parsers focus on learning syntactic log templates but lack the semantic interpretation needed for querying. Directly querying lar...

pgai 信息泄露漏洞

pgai is a set of tools open-sourced by timescale to make it easier to develop RAG, semantic search, and other AI applications using PostgreSQL. An information disclosure vulnerability exists in pgai, which stems from a vulnerability that allows an attacker to steal all secrets in a workflow...

CyFence: Securing Cyber-Physical Controllers Via Trusted Execution Environment

In the last decades, Cyber-physical Systems CPSs have experienced a significant technological evolution and increased connectivity, at the cost of greater exposure to cyber-attacks. Since many CPS are used in safety-critical systems, such attacks entail high risks and potential safety harms...