Adapting under Fire: Multi-Agent Reinforcement Learning for Adversarial Drift in Network Security

Evolving attacks are a critical challenge for the long-term success of Network Intrusion Detection Systems NIDS. The rise of these changing patterns has exposed the limitations of traditional network security methods. While signature-based methods are used to detect different types of attacks, th...

OpenCCA: an Open Framework to Enable Arm CCA Research

Confidential computing has gained traction across major architectures with Intel TDX, AMD SEV-SNP, and Arm CCA. Unlike TDX and SEV-SNP, a key challenge in researching Arm CCA is the absence of hardware support, forcing researchers to develop ad-hoc performance prototypes on non-CCA Arm boards. Th...

FedShield-LLM: a Secure and Scalable Federated Fine-Tuned Large Language Model

Federated Learning FL offers a decentralized framework for training and fine-tuning Large Language Models LLMs by leveraging computational resources across organizations while keeping sensitive data on local devices. It addresses privacy and security concerns while navigating challenges associate...

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification

Purpose: This study proposes a framework for fine-tuning large language models LLMs with differential privacy DP to perform multi-abnormality classification on radiology report text. By injecting calibrated noise during fine-tuning, the framework seeks to mitigate the privacy risks associated wit...

Privacy-Preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models

Prompt learning is a crucial technique for adapting pre-trained multimodal language models MLLMs to user tasks. Federated prompt personalization FPP is further developed to address data heterogeneity and local overfitting, however, it exposes personalized prompts - valuable intellectual assets - ...

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...

Dynamic Encryption-Based Cloud Security Model Using Facial Image and Password-Based Key Generation for Multimedia Data

In this cloud-dependent era, various security techniques, such as encryption, steganography, and hybrid approaches, have been utilized in cloud computing to enhance security, maintain enormous storage capacity, and provide ease of access. However, the absence of data type-specific encryption and...

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...

kernel: Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init()

in linux kernel bluetooth L2CAP, l2capleflowctlinit can cause both div-by-zero and an integer overflow since hdev-lemtu may not fall in the valid range...

Private LoRA Fine-Tuning of Open-Source LLMs with Homomorphic Encryption

Preserving data confidentiality during the fine-tuning of open-source Large Language Models LLMs is crucial for sensitive applications. This work introduces an interactive protocol adapting the Low-Rank Adaptation LoRA technique for private fine-tuning. Homomorphic Encryption HE protects the...

Self-Supervised Transformer-Based Contrastive Learning for Intrusion Detection Systems

As the digital landscape becomes more interconnected, the frequency and severity of zero-day attacks, have significantly increased, leading to an urgent need for innovative Intrusion Detection Systems IDS. Machine Learning-based IDS that learn from the network traffic characteristics and can...

Notes on Univariate Sumcheck

These notes describe an adaptation of the multivariate sumcheck protocol to univariate polynomials interpolated over roots of unity...

DeeCLIP: a Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images

This paper introduces DeeCLIP, a novel framework for detecting AI-generated images using CLIP-ViT and fusion learning. Despite significant advancements in generative models capable of creating highly photorealistic images, existing detection methods often struggle to generalize across different...

SOLIDO: a Robust Watermarking Method for Speech Synthesis Via Low-Rank Adaptation

Whitepaper called SOLIDO: A Robust Watermarking Method For Speech Synthesis Via Low-Rank Adaptation...

MULTI-LF: a Unified Continuous Learning Framework for Real-Time DDoS Detection in Multi-Environment Networks

Detecting Distributed Denial of Service DDoS attacks in Multi-Environment M-En networks presents significant challenges due to diverse malicious traffic patterns and the evolving nature of cyber threats. Existing AI-based detection systems struggle to adapt to new attack strategies and lack...

squid: Request/Response smuggling in HTTP/1.1 and ICAP

SQUID is vulnerable to HTTP request smuggling, caused by chunked decoder lenience, allows a remote attacker to perform Request/Response smuggling past firewall and frontend security systems...

Bluetooth: L2CAP: Fix div-by-zero in l2cap_le_flowctl_init()

...

Patchwork Hackers Target Bhutan with Advanced Brute Ratel C4 Tool

The threat actor known as Patchwork has been linked to a cyber attack targeting entities with ties to Bhutan to deliver the Brute Ratel C4 framework and an updated version of a backdoor called PGoShell. The development marks the first time the adversary has been observed using the red teaming...

SolarMarker Malware Evolves to Resist Takedown Attempts with Multi-Tiered Infrastructure

The persistent threat actors behind the SolarMarker information-stealing malware have established a multi-tiered infrastructure to complicate law enforcement takedown efforts, new findings from Recorded Future show. "The core of SolarMarker's operations is its layered infrastructure, which consis...

kernel: Information leak in l2cap_parse_conf_req in net/bluetooth/l2cap_core.c

An information leak vulnerability was found in the Linux kernel's implementation of logical link control and adaptation protocol L2CAP, part of the Bluetooth stack in the l2capparseconfreq function. An attacker with physical access within the range of standard Bluetooth transmission could use thi...