Computational Attestations of Polynomial Integrity Towards Verifiable Machine-Learning

Machine-learning systems continue to advance at a rapid pace, demonstrating remarkable utility in various fields and disciplines. As these systems continue to grow in size and complexity, a nascent industry is emerging which aims to bring machine-learning-as-a-service MLaaS to market. Outsourcing...

MalGEN: a Generative Agent Framework for Modeling Malicious Software in Cybersecurity

The dual use nature of Large Language Models LLMs presents a growing challenge in cybersecurity. While LLM enhances automation and reasoning for defenders, they also introduce new risks, particularly their potential to be misused for generating evasive, AI crafted malware. Despite this emerging...

STOPA: a Database of Systematic VariaTion of DeePfake Audio for Open-Set Source Tracing and Attribution

A key research area in deepfake speech detection is source tracing - determining the origin of synthesised utterances. The approaches may involve identifying the acoustic model AM, vocoder model VM, or other generation-specific parameters. However, progress is limited by the lack of a dedicated,...

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack

Membership inference attack MIA has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's training set by analyzing the model's output. While traditional...

Practical Adversarial Attacks on Stochastic Bandits Via Fake Data Injection

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more practical threat model, Fake Data Injection, which reflects...

Mal-D2GAN: Double-Detector Based GAN for Malware Generation

Machine learning ML has been developed to detect malware in recent years. Most researchers focused their efforts on improving the detection performance but ignored the robustness of the ML models. In addition, many machine learning algorithms are very vulnerable to intentional attacks. To solve...

LAMDA: a Longitudinal Android Malware Benchmark for Concept Drift Analysis

Machine learning ML-based malware detection systems often fail to account for the dynamic nature of real-world training and test data distributions. In practice, these distributions evolve due to frequent changes in the Android ecosystem, adversarial development of new malware families, and the...

CVE-2024-30915

An issue was discovered in OpenDDS commit b1c534032bb62ad4ae32609778de6b8d6c823a66, allows a local attacker to cause a denial of service and obtain sensitive information via the maxsamples parameter within the DataReaderQoS component...

CVE-2024-30916

An issue was discovered in eProsima FastDDS v.2.14.0 and before, allows a local attacker to cause a denial of service DoS and obtain sensitive information via a crafted maxsamples parameter in DurabilityService QoS component...

CVE-2021-2075

Vulnerability in the Oracle WebLogic Server product of Oracle Fusion Middleware component: Samples. Supported versions that are affected are 10.3.6.0.0, 12.1.3.0.0, 12.2.1.3.0, 12.2.1.4.0 and 14.1.1.0.0. Easily exploitable vulnerability allows unauthenticated attacker with network access via IIOP...

Backdoor Cleaning without External Guidance in MLLM Fine-Tuning

Multimodal Large Language Models MLLMs are increasingly deployed in fine-tuning-as-a-service FTaaS settings, where user-submitted datasets adapt general-purpose models to downstream tasks. This flexibility, however, introduces serious security risks, as malicious fine-tuning can implant backdoors...

Is Artificial Intelligence Generated Image Detection a Solved Problem?

The rapid advancement of generative models, such as GANs and Diffusion models, has enabled the creation of highly realistic synthetic images, raising serious concerns about misinformation, deepfakes, and copyright infringement. Although numerous Artificial Intelligence Generated Image AIGI...

MalVis: a Large-Scale Image-Based Framework and Dataset for Advancing Android Malware Classification

As technology advances, Android malware continues to pose significant threats to devices and sensitive data. The open-source nature of the Android OS and the availability of its SDK contribute to this rapid growth. Traditional malware detection techniques, such as signature-based, static, and...

gstreamer1-plugins-good: OOB-read in qtdemux_parse_samples

A flaw was found in the GStreamer library. Multiple out-of-bounds reads in the MP4/MOV demuxer's sample table parsing and a lack of error checking can cause crashes for certain input files, potentially allowing a malicious actor to trigger an application crash...

RLSA-2024:11193 Moderate: mpg123 security update

The mpg123 packages contain real time MPEG 1.0/2.0/2.5 audio player/decoder for layers 1, 2, and 3 most commonly MPEG 1.0 layer 3 also known as MP3, as well as re-usable decoding and output libraries. Security Fixes: mpg123: Buffer overflow when writing decoded PCM samples CVE-2024-10573 For more...

Adversarial Sample Generation for Anomaly Detection in Industrial Control Systems

Machine learning ML-based intrusion detection systems IDS are vulnerable to adversarial attacks. It is crucial for an IDS to learn to recognize adversarial examples before malicious entities exploit them. In this paper, we generated adversarial samples using the Jacobian Saliency Map Attack JSMA...

Revisiting Data Auditing in Large Vision-Language Models

With the surge of large language models LLMs, Large Vision-Language Models VLMs--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and robotic control. However, VLMs are typically trained on massive web-scraped...

SUSE CVE-2025-22100

In the Linux kernel, the following vulnerability has been resolved: drm/panthor: Fix race condition when gathering fdinfo group samples Commit e16635d88fa0 "drm/panthor: add DRM fdinfo support" failed to protect access to groups with an xarray lock, which could lead to use-after-free errors...

FOG Ransomware Spread by Cybercriminals Claiming Ties to DOGE

This blog details our investigation of malware samples that conceal within them a FOG ransomware payload...

DEBIAN-CVE-2025-22100

In the Linux kernel, the following vulnerability has been resolved: drm/panthor: Fix race condition when gathering fdinfo group samples Commit e16635d88fa0 "drm/panthor: add DRM fdinfo support" failed to protect access to groups with an xarray lock, which could lead to use-after-free errors...