Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial attack that manipulates audio latent representations to...

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

Machine learning ML underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box attacks that exploit model comparisons. Larger models can be mor...

EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models Via Equation Solving and Code Completion

Large language models LLMs, such as ChatGPT, have achieved remarkable success across a wide range of fields. However, their trustworthiness remains a significant concern, as they are still susceptible to jailbreak attacks aimed at eliciting inappropriate or harmful responses. However, existing...

From Rookie to Expert: Manipulating LLMs for Automated Vulnerability Exploitation in Enterprise Software

LLMs democratize software engineering by enabling non-programmers to create applications, but this same accessibility fundamentally undermines security assumptions that have guided software engineering for decades. We show in this work how publicly available LLMs can be socially engineered to...

Incorrect Authorization

Overview Affected versions of this package are vulnerable to Incorrect Authorization due to mishandling access control to private resources. An attacker can gain unauthorized access to private resources by using an API token that is restricted to public resources. Remediation Upgrade...

A Statistical Side-Channel Risk Model for Timing Variability in Lattice-Based Post-Quantum Cryptography

Timing side-channels are an important threat to cryptography that still needs to be addressed in implementations, and the advent of post-quantum cryptography raises this issue because the lattice-based schemes may produce secret-dependent timing variability with the help of complex arithmetic and...

The Imitation Game: Using Large Language Models As Chatbots to Combat Chat-Based Cybercrimes

Chat-based cybercrime has emerged as a pervasive threat, with attackers leveraging real-time messaging platforms to conduct scams that rely on trust-building, deception, and psychological manipulation. Traditional defense mechanisms, which operate on static rules or shallow content filters,...

AutoBaxBuilder: Bootstrapping Code Security Benchmarking

As LLMs see wide adoption in software engineering, the reliable assessment of the correctness and security of LLM-generated code is crucial. Notably, prior work has demonstrated that security is often overlooked, exposing that LLMs are prone to generating code with security vulnerabilities. These...

Assessing the Software Security Comprehension of Large Language Models

Large language models LLMs are increasingly used in software development, but their level of software security expertise remains unclear. This work systematically evaluates the security comprehension of five leading LLMs: GPT-4o-Mini, GPT-5-Mini, Gemini-2.5-Flash, Llama-3.1, and Qwen-2.5, using...

On the Effectiveness of Instruction-Tuning Local LLMs for Identifying Software Vulnerabilities

Large Language Models LLMs show significant promise in automating software vulnerability analysis, a critical task given the impact of security failure of modern software systems. However, current approaches in using LLMs to automate vulnerability analysis mostly rely on using online API-based LL...

Odysseus: Jailbreaking Commercial Multimodal LLM-Integrated Systems Via Dual Steganography

By integrating language understanding with perceptual modalities such as images, multimodal large language models MLLMs constitute a critical substrate for modern AI systems, particularly intelligent agents operating in open and interactive environments. However, their increasing accessibility al...

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...

PT-2025-52634

Name of the Vulnerable Software and Affected Versions Sharp Display Solutions projectors affected versions not specified Sharp Display Solutions NP-P627UL Description A flaw exists in Sharp Display Solutions projectors that allows an attacker to create and run unauthorized firmware. This issue do...

PT-2025-52631

Name of the Vulnerable Software and Affected Versions Sharp projectors affected versions not specified Description A flaw exists in Sharp Display Solutions projectors that involves improper validation of the integrity check value. This could allow an attacker to create and execute unauthorized...

Needles in a Haystack: Using Forensic Network Science to Uncover Insider Trading

Although the automation and digitisation of anti-financial crime investigation has made significant progress in recent years, detecting insider trading remains a unique challenge, partly due to the limited availability of labelled data. To address this challenge, we propose using a data-driven...

CVE-2025-14910

A vulnerability was detected in Edimax BR-6208AC 1.02. This impacts the function handleretr of the component FTP Daemon Service. The manipulation results in path traversal. The attack may be launched remotely. The exploit is now public and may be used. Edimax confirms this issue: "This product is...

PT-2025-52494

Name of the Vulnerable Software and Affected Versions Dive versions prior to 0.11.1 Description Dive is an open-source MCP Host Desktop Application that integrates with function-calling LLMs. A critical Stored Cross-Site Scripting XSS issue exists in the Mermaid diagram rendering component. The...

PT-2025-52408

Name of the Vulnerable Software and Affected Versions ABB T-MAC Plus version 4.0-24 Firebox affected versions not specified Description ABB T-MAC Plus is affected by improper neutralization of input during web page generation, which leads to cross-site scripting XSS, a condition where malicious...

Siemens LOGO! 8 BM Devices Buffer Copy Without Checking Size of Input (CVE-2025-40815)

A vulnerability has been identified in - LOGO! 12/24RCE 6ED1052-1MD08-0BA2 All versions - LOGO! 12/24RCEo 6ED1052-2MD08-0BA2 All versions - LOGO! 230RCE 6ED1052-1FB08-0BA2 All versions - LOGO! 230RCEo 6ED1052-2FB08-0BA2 All versions - LOGO! 24CE 6ED1052-1CC08-0BA2 All versions - LOGO! 24CEo...

Cryptanalysis of Pseudorandom Error-Correcting Codes

Pseudorandom error-correcting codes PRC is a novel cryptographic primitive proposed at CRYPTO 2024. Due to the dual capability of pseudorandomness and error correction, PRC has been recognized as a promising foundational component for watermarking AI-generated content. However, the security of PR...