FedGraM: Defending against Untargeted Attacks in Federated Learning Via Embedding Gram Matrix

Federated Learning FL enables geographically distributed clients to collaboratively train machine learning models by sharing only their local models, ensuring data privacy. However, FL is vulnerable to untargeted attacks that aim to degrade the global model's performance on the underlying data...

Evaluating the Efficacy of LLM Safety Solutions : the Palit Benchmark Dataset

Large Language Models LLMs are increasingly integrated into critical systems in industries like healthcare and finance. Users can often submit queries to LLM-enabled chatbots, some of which can enrich responses with information retrieved from internal databases storing sensitive data. This gives...

Efficient Privacy-Preserving Cross-Silo Federated Learning with Multi-Key Homomorphic Encryption

Federated Learning FL is susceptible to privacy attacks, such as data reconstruction attacks, in which a semi-honest server or a malicious client infers information about other clients' datasets from their model updates or gradients. To enhance the privacy of FL, recent studies combined Multi-Key...

From Nuclear Safety to LLM Security: Applying Non-Probabilistic Risk Management Strategies to Build Safe and Secure LLM-Powered Systems

Large language models LLMs offer unprecedented and growing capabilities, but also introduce complex safety and security challenges that resist conventional risk management. While conventional probabilistic risk analysis PRA requires exhaustive risk enumeration and quantification, the novelty and...

vLLM 代码问题漏洞

vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A code issue vulnerability exists in vLLM versions 0.6.5 through 0.8.4, which stems from PyNcclPipe KV cache transfers not properly limiting the scope of TCPStore interface access...

CVE-2025-48265

Cross-Site Request Forgery CSRF vulnerability in Pektsekye Year Make Model Search for WooCommerce ymm-search allows Cross Site Request Forgery.This issue affects Year Make Model Search for WooCommerce: from n/a through = 1.0.11...

K000151398: PyTorch vulnerability CVE-2025-32434

Security Advisory Description PyTorch is a Python package that provides tensor computation with strong GPU acceleration and deep neural networks built on a tape-based autograd system. In version 2.5.1 and prior, a Remote Command Execution RCE vulnerability exists in PyTorch when loading a model...

BeamClean: Language Aware Embedding Reconstruction

In this work, we consider an inversion attack on the obfuscated input embeddings sent to a language model on a server, where the adversary has no access to the language model or the obfuscation mechanism and sees only the obfuscated embeddings along with the model's embedding table. We propose...

Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy

Federated Learning with client-level differential privacy DP provides a promising framework for collaboratively training models while rigorously protecting clients' privacy. However, classic approaches like DP-FedAvg struggle when clients have heterogeneous privacy requirements, as they must...

The Hidden Dangers of Browsing AI Agents

Autonomous browsing agents powered by large language models LLMs are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface. This paper presents a comprehensive security evaluation of...

Network-Wide Quantum Key Distribution with Onion Routing Relay

The advancement of quantum computing threatens classical cryptographic methods, necessitating the development of secure quantum key distribution QKD solutions for QKD Networks QKDN. In this paper, a novel key distribution protocol, Onion Routing Relay ORR, that integrates onion routing OR with...

MorphMark: Flexible Adaptive Watermarking for Large Language Models

Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models LLMs. However, existing watermark methods often struggle with a fundamental dilemma: improving watermark effectiveness the...

MCP Guardian: a Security-First Layer for Safeguarding MCP-Based AI System

As Agentic AI gain mainstream adoption, the industry invests heavily in model capabilities, achieving rapid leaps in reasoning and quality. However, these systems remain largely confined to data silos, and each new integration requires custom logic that is difficult to scale. The Model Context...

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

LLM-based autonomous agents possess capabilities such as reasoning, tool invocation, and environment interaction, enabling the execution of complex multi-step tasks. The internal reasoning process, i.e., thought, of behavioral trajectory significantly influences tool usage and subsequent actions...

Network-Wide Quantum Key Distribution with Onion Routing Relay (Conference Version)

The advancement of quantum computing threatens classical cryptographic methods, necessitating the development of secure quantum key distribution QKD solutions for QKD Networks QKDN. In this paper, a novel key distribution protocol, Onion Routing Relay ORR, that integrates onion routing OR with...

WordPress plugin Year Make Model Search for WooCommerce 跨站请求伪造漏洞

WordPress and WordPress plugin are both products of the WordPress Foundation, a blogging platform developed in PHP. The platform supports personal blog sites on PHP and MySQL servers.WordPress plugin is an application plugin. A cross-site request forgery vulnerability exists in the WordPress plug...

CVE-2025-22233

CVE-2024-38820 ensured Locale-independent, lowercase conversion for both the configured disallowedFields patterns and for request parameter names. However, there are still cases where it is possible to bypass the disallowedFields checks. Affected Spring Products and Versions Spring Framework: 6.2...

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...

Improving LLM Outputs against Jailbreak Attacks with Expert Model Integration

Using LLMs in a production environment presents security challenges that include vulnerabilities to jailbreaks and prompt injections, which can result in harmful outputs for humans or the enterprise. The challenge is amplified when working within a specific domain, as topics generally accepted fo...

CVE-2025-4834

A vulnerability was found in TOTOLINK A702R, A3002R and A3002RU 3.0.0-B20230809.1615. It has been classified as critical. Affected is an unknown function of the file /boafrm/formSetLg of the component HTTP POST Request Handler. The manipulation of the argument submit-url leads to buffer overflow...