llisoft MTA Maita Training System 注入漏洞

The llisoft MTA Maita Training System is a training system from China Dongke llisoft. An injection vulnerability exists in version 4.5 of the llisoft MTA Maita Training System, which results from an SQL injection due to the operation of the parameter stTypeIds...

PT-2025-22912 · Llisoft · Llisoft Mta Maita Training System

Name of the Vulnerable Software and Affected Versions: llisoft MTA Maita Training System version 4.5 Description: A critical vulnerability was found in the llisoft MTA Maita Training System, affecting the AdminShitiListRequestVo function of the file...

Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs

As Artificial Intelligence AI systems, particularly those based on machine learning ML, become integral to high-stakes applications, their probabilistic and opaque nature poses significant challenges to traditional verification and validation methods. These challenges are exacerbated in regulated...

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...

MADCAT: Combating Malware Detection under Concept Drift with Test-Time Adaptation

We present MADCAT, a self-supervised approach designed to address the concept drift problem in malware detection. MADCAT employs an encoder-decoder architecture and works by test-time training of the encoder on a small, balanced subset of the test-time data using a self-supervised objective. Duri...

A Linear Approach to Data Poisoning

We investigate the theoretical foundations of data poisoning attacks in machine learning models. Our analysis reveals that the Hessian with respect to the input serves as a diagnostic tool for detecting poisoning, exhibiting spectral signatures that characterize compromised datasets. We use rando...

Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems

Autonomous driving systems ADS increasingly rely on deep learning-based perception models, which remain vulnerable to adversarial attacks. In this paper, we revisit adversarial attacks and defense methods, focusing on road sign recognition and lead object detection and prediction e.g., relative...

CVE-2020-25459

An issue was discovered in function synctree in heterodecisiontreeguest.py in WeBank FATE Federated AI Technology Enabler 0.1 through 1.4.2 allows attackers to read sensitive information during the training process of machine learning joint modeling...

CVE-2019-15487

DfE School Experience before v16333-GA has XSS via a teacher training URL...

INE Security Partners with Abadnet Institute for Cybersecurity Training Programs in Saudi Arabia

Cary, North Carolina, 22nd May 2025, CyberNewsWire...

ReCopilot: Reverse Engineering Copilot in Binary Analysis

Binary analysis plays a pivotal role in security domains such as malware detection and vulnerability discovery, yet it remains labor-intensive and heavily reliant on expert knowledge. General-purpose large language models LLMs perform well in programming analysis on source code, while...

Covert Attacks on Machine Learning Training in Passively Secure MPC

Secure multiparty computation MPC allows data owners to train machine learning models on combined data while keeping the underlying training data private. The MPC threat model either considers an adversary who passively corrupts some parties without affecting their overall behavior, or an adversa...

Training-Free Watermarking for Autoregressive Image Generation

Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored...

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...

An Alignment between the CRA'S Essential Requirements and the ATT&CK'S Mitigations

The paper presents an alignment evaluation between the mitigations present in the MITRE's ATT&CK framework and the essential cyber security requirements of the recently introduced Cyber Resilience Act CRA in the European Union. In overall, the two align well with each other. With respect to the...

PoLO: Proof-Of-Learning and Proof-Of-Ownership at Once with Chained Watermarking

Machine learning models are increasingly shared and outsourced, raising requirements of verifying training effort Proof-of-Learning, PoL to ensure claimed performance and establishing ownership Proof-of-Ownership, PoO for transactions. When models are trained by untrusted parties, PoL and PoO mus...

R1dacted: Investigating Local Censorship in DeepSeek'S R1 Language Model

DeepSeek recently released R1, a high-performing large language model LLM optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performance, even surpassing leading reasoning models like OpenAI's o1 on several benchmarks. However, emerging reports suggest...

Trend Joins NVIDIA to Secure AI Infrastructure with NVIDIA

Together, we are focused on securing the full AI lifecycle—from development and training to deployment and inference—across cloud, data center, and AI factories...

Self-Destructive Language Model

Harmful fine-tuning attacks pose a major threat to the security of large language models LLMs, allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment, they fail to address models' inherent "trainability" on harmfu...

Facial Recognition Leveraging Generative Adversarial Networks

Face recognition performance based on deep learning heavily relies on large-scale training data, which is often difficult to acquire in practical applications. To address this challenge, this paper proposes a GAN-based data augmentation method with three key contributions: 1 a residual-embedded...