CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks

Multimodal Large Language Models MLLMs achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single modality, recent studies reveal implicit attacks, in which...

Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution

This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The task required designing an adversarial attack against a provided classification model that maximizes misclassification while...

DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection

Over the last decade, machine learning has been extensively applied to identify malicious Android applications. However, such approaches remain vulnerable against adversarial examples, i.e., examples that are subtly manipulated to fool a machine learning model into making incorrect predictions...

SASER: Stego Attacks on Open-Source LLMs

Open-source large language models LLMs have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source codes, model parameters, and training data lays the groundwork for transparenc...

EUVD-2025-19819

Malicious code in bioql PyPI...

FakeSound2: a Benchmark for Explainable and Generalizable Deepfake Sound Detection

The rapid development of generative audio raises ethical and security concerns stemming from forged data, making deepfake sound detection an important safeguard against the malicious use of such technologies. Although prior studies have explored this task, existing methods largely focus on binary...

Fluid-Antenna-Aided AAV Secure Communications in Eavesdropper Uncertain Location

For autonomous aerial vehicle AAV secure communications, traditional designs based on fixed position antenna FPA lack sufficient spatial degrees of freedom DoF, which leaves the line-of-sight-dominated AAV links vulnerable to eavesdropping. To overcome this problem, this paper proposes a framewor...

jaeles

This is a powerful, flexible, and easily extensible framework written in Go for building your own Web Application Scanner. The framework is called Jaeles and is designed to be highly customizable. It has a modular architecture, allowing users to easily add or remove plugins to suit their needs. T...

CVE-2025-32100

CVE-2025-32100 affects Samsung Mobile Processor, Wearable Processor, and Modem Exynos/Modem families (multiple models listed). Root cause: a buffer copy programming mistake leading to out-of-bounds writes via malformed ROHC packets. Impact per NVD metrics: Network attack vector, low attack comple...

PT-2025-35595

Name of the Vulnerable Software and Affected Versions: Samsung Mobile Processor, Wearable Processor, and Modem Exynos 980 Samsung Mobile Processor, Wearable Processor, and Modem Exynos 990 Samsung Mobile Processor, Wearable Processor, and Modem Exynos 850 Samsung Mobile Processor, Wearable...

VULSOVER: Vulnerability Detection Via LLM-Driven Constraint Solving

Traditional vulnerability detection methods rely heavily on predefined rule matching, which often fails to capture vulnerabilities accurately. With the rise of large language models LLMs, leveraging their ability to understand code semantics has emerged as a promising direction for achieving more...

False Data-Injection Attack Detection in Cyber-Physical Systems: a Wasserstein Distributionally Robust Reachability Optimization Approach

Cyber-physical system CPS is the foundational backbone of modern critical infrastructures, so ensuring its security and resilience against cyber-attacks is of pivotal importance. This paper addresses the challenge of designing anomaly detectors for CPS under false-data injection FDI attacks and...

MAL-2025-32335 Malicious code in robust-free-bootstrap-admin-template (npm)

The package robust-free-bootstrap-admin-template was found to contain malicious code...

MirGuard: Towards a Robust Provenance-Based Intrusion Detection System against Graph Manipulation Attacks

Learning-based Provenance-based Intrusion Detection Systems PIDSes have become essential tools for anomaly detection in host systems due to their ability to capture rich contextual and structural information, as well as their potential to detect unknown attacks. However, recent studies have shown...

AuthPrint: Fingerprinting Generative Models against Malicious Model Providers

Generative models are increasingly adopted in high-stakes domains, yet current deployments offer no mechanisms to verify the origin of model outputs. We address this gap by extending model fingerprinting techniques beyond the traditional collaborative setting to one where the model provider may a...

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech

This study introduces LENS-DF, a novel and comprehensive recipe for training and evaluating audio deepfake detection and temporal localization under complicated and realistic audio conditions. The generation part of the recipe outputs audios from the input dataset with several critical...

SHIELD: a Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks

Audio plays a crucial role in applications like speaker verification, voice-enabled smart devices, and audio conferencing. However, audio manipulations, such as deepfakes, pose significant risks by enabling the spread of misinformation. Our empirical analysis reveals that existing methods for...

Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs

Recent studies have shown that Large Language Models LLMs are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a phrase and focus on the attack's effectiveness, offering limite...

Differentially Private Federated Low Rank Adaptation beyond Fixed-Matrix

Large language models LLMs typically require fine-tuning for domain-specific tasks, and LoRA offers a computationally efficient approach by training low-rank adapters. LoRA is also communication-efficient for federated LLMs when multiple users collaboratively fine-tune a global LLM model without...

When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-Of-Distribution Trap Is All You Need

Data-free knowledge distillation DFKD transfers knowledge from a teacher to a student without access the real in-distribution ID data. Its common solution is to use a generator to synthesize fake data and use them as a substitute for real ID data. However, existing works typically assume teachers...