FIST: a Structured Threat Modeling Framework for Fraud Incidents

Fraudulent activities are rapidly evolving, employing increasingly diverse and sophisticated methods that pose serious threats to individuals, organizations, and society. This paper proposes the FIST Framework Fraud Incident Structured Threat Framework, an innovative structured threat modeling...

TracLLM: a Generic Framework for Attributing Long Context LLMs

Long context large language models LLMs are deployed in many real-world applications such as RAG, agent, and broad LLM-integrated applications. Given an instruction and a long context e.g., documents, PDF files, webpages, a long context LLM can generate an output grounded in the provided context,...

Hybrid Stabilization Protocol for Cross-Chain Digital Assets Using Adaptor Signatures and AI-Driven Arbitrage

Stablecoins face an unresolved trilemma of balancing decentralization, stability, and regulatory compliance. We present a hybrid stabilization protocol that combines crypto-collateralized reserves, algorithmic futures contracts, and cross-chain liquidity pools to achieve robust price adherence...

The vulnerability of the get_article_urls() function in the KnowledgeBaseWebReader class of the LlamaIndex framework for working with large language models allows a attacker to trigger a service denial.

The vulnerability of the getarticleurls function in the KnowledgeBaseWebReader class of the LlamaIndex framework, which is used for working with large language models, is related to an uncontrolled resource consumption when processing the maxdepth parameter. Exploiting this vulnerability could...

QA-HFL: Quality-Aware Hierarchical Federated Learning for Resource-Constrained Mobile Devices with Heterogeneous Image Quality

This paper introduces QA-HFL, a quality-aware hierarchical federated learning framework that efficiently handles heterogeneous image quality across resource-constrained mobile devices. Our approach trains specialized local models for different image quality levels and aggregates their features...

Security Bulletin: Multiple security vulnerabilities affecting IBM Knowledge Catalog for IBM Cloud Pak for Data

Summary Multiple security vulnerabilities impacting IBM Knowledge Catalog for IBM Cloud Pak for Data. These vulnerabilities have been addressed. Vulnerability Details CVEID:CVE-2023-3635 DESCRIPTION: Okio GzipSource is vulnerable to a denial of service, caused by unhandled exception. By sending a...

Security Bulletin: Multiple security vulnerabilities affecting IBM Knowledge Catalog for IBM Cloud Pak for Data

Summary Multiple security vulnerabilities impacting IBM Knowledge Catalog for IBM Cloud Pak for Data. These vulnerabilities have been addressed. Vulnerability Details CVEID:CVE-2023-28155 DESCRIPTION: Node.js Request module is vulnerable to server-side request forgery, caused by a cross-protocol...

Scaling DeFi with ZK Rollups: Design, Deployment, and Evaluation of a Real-Time Proof-Of-Concept

Ethereum's scalability limitations pose significant challenges for the adoption of decentralized applications dApps. Zero-Knowledge Rollups ZK Rollups present a promising solution, bundling transactions off-chain and submitting validity proofs on-chain to enhance throughput and efficiency. In thi...

When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs

Knowledge files have been widely used in large language model LLM agents, such as GPTs, to improve response quality. However, concerns about the potential leakage of knowledge files have grown significantly. Existing studies demonstrate that adversarial prompts can induce GPTs to leak knowledge...

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these mechanisms to discriminate or unjustly deny services under...

Head Start 安全漏洞

Head Start is a web-based knowledge mapping software open-sourced by Open Knowledge Maps. It is designed to give researchers a head start in literature review hence the name. A security vulnerability exists in the v7 version of Head Start that stems from improper handling of the url parameter in...

Privacy-Preserving Inconsistency Measurement

We investigate a new form of privacy-preserving inconsistency measurement for multi-party communication. Intuitively, for two knowledge bases KA, KB of two agents A, B, our results allow to quantitatively assess the degree of inconsistency for KA U KB without having to reveal the actual contents ...

Spa-VLM: Stealthy Poisoning Attacks on RAG-Based VLM

With the rapid development of the Vision-Language Model VLM, significant progress has been made in Visual Question Answering VQA tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To address this issue, recent research has introduced...

DP-RTFL: Differentially Private Resilient Temporal Federated Learning for Trustworthy AI in Regulated Industries

Federated Learning FL has emerged as a critical paradigm for enabling privacy-preserving machine learning, particularly in regulated sectors such as finance and healthcare. However, standard FL strategies often encounter significant operational challenges related to fault tolerance, system...

Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs

As Artificial Intelligence AI systems, particularly those based on machine learning ML, become integral to high-stakes applications, their probabilistic and opaque nature poses significant challenges to traditional verification and validation methods. These challenges are exacerbated in regulated...

TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks

Verification of the integrity of deep learning inference is crucial for understanding whether a model is being applied correctly. However, such verification typically requires access to model weights and potentially sensitive or private training data. So-called Zero-knowledge Succinct...

CVE-2024-46326

Public Knowledge Project pkp-lib 3.4.0-7 and earlier is vulnerable to Open redirect due to a lack of input sanitization in the logout function...

CVE-2024-6229

A stored cross-site scripting XSS vulnerability exists in the 'Upload Knowledge' feature of stangirard/quivr, affecting the latest version. Users can upload files via URL, which allows the insertion of malicious JavaScript payloads. These payloads are stored on the server and executed whenever an...

CVE-2024-38533

ZKsync Era is a layer 2 rollup that uses zero-knowledge proofs to scale Ethereum. There is possible invalid stack access due to the addresses used to access the stack not properly being converted to cells. This issue has been patched in version 1.5.0...

CVE-2024-56137

MaxKB, which stands for Max Knowledge Base, is an open source knowledge base question-answering system based on a large language model and retrieval-augmented generation RAG. Prior to version 1.9.0, a remote command execution vulnerability exists in the module of function library. The vulnerabili...