Transaction Fee Mechanism Design for Leaderless Blockchain Protocols

We initiate the study of transaction fee mechanism design for blockchain protocols in which multiple block producers contribute to the production of each block. Our contributions include: - We propose an extensive-form multi-stage game model to reason about the game theory of multi-proposer...

Efficient and Stealthy Jailbreak Attacks Via Adversarial Prompt Distillation from LLMs to SLMs

Attacks on large language models LLMs in jailbreaking scenarios raise many security and ethical issues. Current jailbreak attack methods face problems such as low efficiency, high computational cost, and poor cross-model adaptability and versatility, which make it difficult to cope with the rapid...

InspireMusic 代码问题漏洞

InspireMusic is an open source music, song, and audio generation tool from FunAudioLLM. A code issue vulnerability exists in InspireMusic that stems from a deserialization issue in the file inspiremusic/cli/model.py...

RADEP: a Resilient Adaptive Defense Framework against Model Extraction Attacks

Machine Learning as a Service MLaaS enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks, where adversaries repeatedly query the application programming...

Evaluating Query Efficiency and Accuracy of Transfer Learning-Based Model Extraction Attack in Federated Learning

Federated Learning FL is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property IP threats. Model extraction ME attacks pose a significant risk to Machine Learning as a Service MLaaS platforms, enabling attackers to replicate...

Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models

State-of-the-art membership inference attacks MIAs typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models LLMs. As a result, prior research has either relied on weaker attacks that avoid training reference models e.g.,...

Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair

The rapid advancement of bug-finding techniques has led to the discovery of more vulnerabilities than developers can reasonably fix, creating an urgent need for effective Automated Program Repair APR methods. However, the complexity of modern bugs often makes precise root cause analysis difficult...

Exemplifying Emerging Phishing: QR-Based Browser-In-The-Browser (BiTB) Attack

Lately, cybercriminals constantly formulate productive approaches to exploit individuals. This article exemplifies an innovative attack, namely QR-based Browser-in-The-Browser BiTB, using proficiencies of Large Language Model LLM i.e. Google Gemini. The presented attack is a fusion of two emergin...

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

Retrieval-Augmented Generation RAG has proven effective in mitigating hallucinations in large language models by incorporating external knowledge during inference. However, this integration introduces new security vulnerabilities, particularly to poisoning attacks. Although prior work has explore...

CVE-2025-0708

A vulnerability was found in fumiao opencms 2.2. It has been declared as problematic. This vulnerability affects unknown code of the file /admin/model/addOrUpdate of the component Add Model Management Page. The manipulation of the argument 模板前缀 leads to cross site scripting. The attack can be...

CVE-2024-7038

An information disclosure vulnerability exists in open-webui version 0.3.8. The vulnerability is related to the embedding model update feature under admin settings. When a user updates the model path, the system checks if the file exists and provides different error messages based on the existenc...

CVE-2024-7784

During internal Axis Security Development Model ASDM threat-modelling, a flaw was found in the protection for device tampering commonly known as Secure Boot in AXIS OS making it vulnerable to a sophisticated attack to bypass this protection. To Axis' knowledge, there are no known exploits of the...

CVE-2024-5616

A Cross-Site Request Forgery CSRF vulnerability exists in mudler/LocalAI versions up to and including 2.15.0, which allows attackers to trick victims into deleting installed models. By crafting a malicious HTML page, an attacker can cause the deletion of a model, such as 'gpt-4-vision-preview',...

CVE-2024-34359

llama-cpp-python is the Python bindings for llama.cpp. llama-cpp-python depends on class Llama in llama.py to load .gguf llama.cpp or Latency Machine Learning Models. The init constructor built in the Llama takes several parameters to configure the loading and running of the model. Other than NUM...

CVE-2024-3402

A stored Cross-Site Scripting XSS vulnerability existed in version 20240121 of gaizhenbiao/chuanhuchatgpt due to inadequate sanitization and validation of model output data. Despite user-input validation efforts, the application fails to properly sanitize or validate the output from the model,...

CVE-2024-3102

A JSON Injection vulnerability exists in the mintplex-labs/anything-llm application, specifically within the username parameter during the login process at the /api/request-token endpoint. The vulnerability arises from improper handling of values, allowing attackers to perform brute force attacks...

CVE-2024-30559

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in Maurice Spin 360 deg and 3D Model Viewer allows Stored XSS.This issue affects Spin 360 deg and 3D Model Viewer: from n/a through 1.2.7...

CVE-2024-56516

free-one-api allows users to access large language model reverse engineering libraries through the standard OpenAI API format. In versions up to and including 1.0.1, MD5 is used to hash passwords before sending them to the backend. MD5 is a cryptographically broken hashing algorithm and is no...

CVE-2024-35238

Minder by Stacklok is an open source software supply chain security platform. Minder prior to version 0.0.51 is vulnerable to a denial-of-service DoS attack which could allow an attacker to crash the Minder server and deny other users access to it. The root cause of the vulnerability is that...

CVE-2024-7223

A vulnerability has been found in SourceCodester Lot Reservation Management System 1.0 and classified as critical. Affected by this vulnerability is an unknown functionality of the file /viewmodel.php. The manipulation of the argument id leads to sql injection. The attack can be launched remotely...