Red-Teaming Text-To-Image Systems by Rule-Based Preference Modeling

Text-to-image T2I models raise ethical and safety concerns due to their potential to generate inappropriate or harmful images. Evaluating these models' security through red-teaming is vital, yet white-box approaches are limited by their need for internal access, complicating their use with...

PrivATE: Differentially Private Confidence Intervals for Average Treatment Effects

The average treatment effect ATE is widely used to evaluate the effectiveness of drugs and other medical interventions. In safety-critical applications like medicine, reliable inferences about the ATE typically require valid uncertainty quantification, such as through confidence intervals CIs...

BitHydra: Towards Bit-Flip Inference Cost Attack against Large Language Models

Large language models LLMs have shown impressive capabilities across a wide range of applications, but their ever-increasing size and resource demands make them vulnerable to inference cost attacks, where attackers induce victim LLMs to generate the longest possible output content. In this paper,...

CVE-2025-5202

A vulnerability was found in Open Asset Import Library Assimp 5.4.3. It has been declared as problematic. Affected by this vulnerability is the function HL1MDLLoader::validateheader of the file assimp/code/AssetLib/MDL/HalfLife/HL1MDLLoader.cpp. The manipulation leads to out-of-bounds read. An...

UBUNTU-CVE-2025-5202

A vulnerability was found in Open Asset Import Library Assimp 5.4.3. It has been declared as problematic. Affected by this vulnerability is the function HL1MDLLoader::validateheader of the file assimp/code/AssetLib/MDL/HalfLife/HL1MDLLoader.cpp. The manipulation leads to out-of-bounds read. An...

DEBIAN-CVE-2025-5200

A vulnerability was found in Open Asset Import Library Assimp 5.4.3 and classified as problematic. This issue affects the function MDLImporter::InternReadFileQuake1 of the file assimp/code/AssetLib/MDL/MDLLoader.cpp. The manipulation leads to out-of-bounds read. It is possible to launch the attac...

Out-of-bounds Read

Overview Affected versions of this package are vulnerable to Out-of-bounds Read through the MDLImporter::InternReadFileQuake1 function. An attacker can read data outside the intended buffer boundaries by manipulating the input data to the function. Remediation There is no fixed version for assimp...

DEBIAN-CVE-2025-5169

A vulnerability classified as problematic has been found in Open Asset Import Library Assimp 5.4.3. This affects the function MDLImporter::InternReadFile3DGSMDL345 of the file assimp/code/AssetLib/MDL/MDLLoader.cpp. The manipulation leads to out-of-bounds read. Local access is required to approac...

UBUNTU-CVE-2025-5169

A vulnerability classified as problematic has been found in Open Asset Import Library Assimp 5.4.3. This affects the function MDLImporter::InternReadFile3DGSMDL345 of the file assimp/code/AssetLib/MDL/MDLLoader.cpp. The manipulation leads to out-of-bounds read. Local access is required to approac...

A Framework for Combined Transaction Posting and Pricing for Layer 2 Blockchains

This paper presents a comprehensive framework for transaction posting and pricing in Layer 2 L2 blockchain systems, focusing on challenges stemming from fluctuating Layer 1 L1 gas fees and the congestion issues within L2 networks. Existing methods have focused on the problem of optimal posting...

📄 Grandstream GSD3710 1.0.11.13 Stack Buffer Overflow

Grandstream GSD3710 version 1.0.11.13 suffers from a stack buffer overflow vulnerability. !/usr/bin/env python3 Exploit Title: Grandstream GSD3710 1.0.11.13 - Stack Buffer Overflow Google Dork: if applicable Date: 2025-05-23 Exploit Author: Pepelux user in ExploitDB Vendor Homepage:...

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...

MixBridge: Heterogeneous Image-To-Image Backdoor Attack through Mixture of Schrödinger Bridges

This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-attack scenarios and are limited to Gaussian noise input models. To fill this gap...

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.,...

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...

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...