EASE: Practical and Efficient Safety Alignment for Small Language Models

Small language models SLMs are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While...

Metasploit Wrap Up 10/09/2025

Meterpreter: Kickstarting Windows ARM64 and Reducing Memory Footprint This Metasploit-Framework release includes two important milestones for our payloads capability. The first, spearheaded by community contributor Alexander "xaitax" Hagenah, is an enhancement of our ReflectiveLoader, a crucial...

ANCORA: Accurate Intrusion Recovery for Web Applications

Modern web application recovery presents a critical dilemma. Coarse-grained snapshot rollbacks cause unacceptable data loss for legitimate users. Surgically removing an attack's impact is hindered by a fundamental challenge in high-concurrency environments: it is difficult to attribute resulting...

EUVD-2006-0440

Malware in sbrugna...

Ruckus Wireless ICX Switches Integer Overflow or Wraparound (CVE-2019-11477)

Three flaws were found in the Linux kernel's handling of TCP networking. The most severe vulnerability could allow a remote attacker to trigger a kernel panic in systems running the affected software and, as a result, impact the system's availability. The issues have been assigned multiple CVEs:...

VehiclePassport: a GAIA-X-Aligned, Blockchain-Anchored Privacy-Preserving, Zero-Knowledge Digital Passport for Smart Vehicles

Modern vehicles accumulate fragmented lifecycle records across OEMs, owners, and service centers that are difficult to verify and prone to fraud. We propose VehiclePassport, a GAIA-X-aligned digital passport anchored on blockchain with zero-knowledge proofs ZKPs for privacy-preserving verificatio...

Zero Trust + AI: Privacy in the Age of Agentic AI

We used to think of privacy as a perimeter problem: about walls and locks, permissions, and policies. But in a world where artificial agents are becoming autonomous actors — interacting with data, systems, and humans without constant oversight — privacy is no longer about control. It's about trus...

Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference

Global KV-cache sharing has emerged as a key optimization for accelerating large language model LLM inference. However, it exposes a new class of timing side-channel attacks, enabling adversaries to infer sensitive user inputs via shared cache entries. Existing defenses, such as per-user isolatio...

SelectiveShield: Lightweight Hybrid Defense against Gradient Leakage in Federated Learning

Federated Learning FL enables collaborative model training on decentralized data but remains vulnerable to gradient leakage attacks that can reconstruct sensitive user information. Existing defense mechanisms, such as differential privacy DP and homomorphic encryption HE, often introduce a...

SenseCrypt: Sensitivity-Guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios

Homomorphic Encryption HE prevails in securing Federated Learning FL, but suffers from high overhead and adaptation cost. Selective HE methods, which partially encrypt model parameters by a global mask, are expected to protect privacy with reduced overhead and easy adaptation. However, in...

Evaluating Selective Encryption against Gradient Inversion Attacks

Gradient inversion attacks pose significant privacy threats to distributed training frameworks such as federated learning, enabling malicious parties to reconstruct sensitive local training data from gradient communications between clients and an aggregation server during the aggregation process...

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...

Secure Distributed Learning for CAVs: Defending against Gradient Leakage with Leveled Homomorphic Encryption

Federated Learning FL enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning in domains like Connected and Autonomous Vehicles CAVs. However, recent studies have shown that exchanged model...

SECNEURON: Reliable and Flexible Abuse Control in Local LLMs Via Hybrid Neuron Encryption

Large language models LLMs with diverse capabilities are increasingly being deployed in local environments, presenting significant security and controllability challenges. These locally deployed LLMs operate outside the direct control of developers, rendering them more susceptible to abuse...

Compact and Selective Disclosure for Verifiable Credentials

Self-Sovereign Identity SSI is a novel identity model that empowers individuals with full control over their data, enabling them to choose what information to disclose, with whom, and when. This paradigm is rapidly gaining traction worldwide, supported by numerous initiatives such as the European...

SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA

Federated fine-tuning of large language models LLMs is critical for improving their performance in handling domain-specific tasks. However, prior work has shown that clients' private data can actually be recovered via gradient inversion attacks. Existing privacy preservation techniques against su...

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...

Multiparty Selective Disclosure Using Attribute-Based Encryption

This study proposes a mechanism for encrypting SD-JWT Selective Disclosure JSON Web Token Disclosures using Attribute-Based Encryption ABE to enable flexible access control on the basis of the Verifier's attributes. By integrating Ciphertext-Policy ABE CP-ABE into the existing SD-JWT framework, t...

Learning from the Good Ones: Risk Profiling-Based Defenses against Evasion Attacks on DNNs

Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks DNN to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to trick the DNN into making wrong decisions at inference time...

Securing Immersive 360 Video Streams through Attribute-Based Selective Encryption

Delivering high-quality, secure 360� video content introduces unique challenges, primarily due to the high bitrates and interactive demands of immersive media. Traditional HTTPS-based methods, although widely used, face limitations in computational efficiency and scalability when securing these...