CVE-2025-5173

CVE-2025-5173 affects HumanSignal label-studio-ml-backend, specifically the PT File Handler's neural_nets.py load function. The vulnerability arises from manipulation of the path argument, leading to deserialization. This is described as a local attack with the affected release up to 9fb7f4aa1866...

Weak-Jamming Detection in IEEE 802.11 Networks: Techniques, Scenarios and Mobility

State-of-the-art solutions detect jamming attacks ex-post, i.e., only when jamming has already disrupted the wireless communication link. In many scenarios, e.g., mobile networks or static deployments distributed over a large geographical area, it is often desired to detect jamming at the early...

TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks

Verification of the integrity of deep learning inference is crucial for understanding whether a model is being applied correctly. However, such verification typically requires access to model weights and potentially sensitive or private training data. So-called Zero-knowledge Succinct...

CVE-2024-21792

Time-of-check Time-of-use race condition in IntelR Neural Compressor software before version 2.5.0 may allow an authenticated user to potentially enable information disclosure via local access...

CVE-2024-37181

Time-of-check time-of-use race condition in some IntelR Neural Compressor software before version v3.0 may allow an authenticated user to potentially enable information disclosure via adjacent access...

CVE-2024-36284

Improper input validation in some IntelR Neural Compressor software before version v3.0 may allow an authenticated user to potentially enable escalation of privilege via adjacent access...

CVE-2023-28543

A malformed DLC can trigger Memory Corruption in SNPE library due to out of bounds read, such as by loading an untrusted model e.g. from a remote source...

CVE-2023-26085

A possible out-of-bounds read and write due to an improper length check of shared memory was discovered in Arm NN Android-NN-Driver before 23.02...

Towards Anonymous Neural Network Inference

We introduce funion, a system providing end-to-end sender-receiver unlinkability for neural network inference. By leveraging the Pigeonhole storage protocol and BACAP blinding-and-capability scheme from the Echomix anonymity system, funion inherits the provable security guarantees of modern...

Sec5GLoc: Securing 5G Indoor Localization Via Adversary-Resilient Deep Learning Architecture

Emerging 5G millimeter-wave and sub-6 GHz networks enable high-accuracy indoor localization, but security and privacy vulnerabilities pose serious challenges. In this paper, we identify and address threats including location spoofing and adversarial signal manipulation against 5G-based indoor...

CVE-2020-29540

API calls in the Translation API feature in Systran Pure Neural Server before 9.7.0 allow a threat actor to use the Systran Pure Neural Server as a Denial-of-Service proxy by sending a large amount of translation requests to a destination host on any given TCP port regardless of whether a web...

CVE-2020-29539

A Cross-Site Scripting XSS issue in WebUI Translation in Systran Pure Neural Server before 9.7.0 allows a threat actor to have a remote authenticated user run JavaScript from a malicious site...

CVE-2019-10844

nbla/logger.cpp in libnnabla.a in Sony Neural Network Libraries aka nnabla through v1.0.14 relies on the HOME environment variable, which might be untrusted...

Privacy-Aware Cyberterrorism Network Analysis Using Graph Neural Networks and Federated Learning

Cyberterrorism poses a formidable threat to digital infrastructures, with increasing reliance on encrypted, decentralized platforms that obscure threat actor activity. To address the challenge of analyzing such adversarial networks while preserving the privacy of distributed intelligence data, we...

EC-LDA : Label Distribution Inference Attack against Federated Graph Learning with Embedding Compression

Graph Neural Networks GNNs have been widely used for graph analysis. Federated Graph Learning FGL is an emerging learning framework to collaboratively train graph data from various clients. However, since clients are required to upload model parameters to the server in each round, this provides t...

AI-Driven Dynamic Firewall Optimization Using Reinforcement Learning for Anomaly Detection and Prevention

The growing complexity of cyber threats has rendered static firewalls increasingly ineffective for dynamic, real-time intrusion prevention. This paper proposes a novel AI-driven dynamic firewall optimization framework that leverages deep reinforcement learning DRL to autonomously adapt and update...

PRUNE: a Patching Based Repair Framework for Certifiable Unlearning of Neural Networks

It is often desirable to remove a.k.a. unlearn a specific part of the training data from a trained neural network model. A typical application scenario is to protect the data holder's right to be forgotten, which has been promoted by many recent regulation rules. Existing unlearning methods invol...

Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge

Artificial neural network pruning is a method in which artificial neural network sizes can be reduced while attempting to preserve the predicting capabilities of the network. This is done to make the model smaller or faster during inference time. In this work we analyze the ability of a selection...

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?

Low rank adaptation LoRA has emerged as a prominent technique for fine-tuning large language models LLMs thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural properties of LoRA, its behavior upon training-time attacks...

Friday Squid Blogging: Pet Squid Simulation

From Hackaday.com, this is a neural network simulation of a pet squid. Autonomous Behavior: The squid moves autonomously, making decisions based on his current state hunger, sleepiness, etc.. Implements a vision cone for food detection, simulating realistic foraging behavior. Neural network can...