Your Agent Can Defend Itself against Backdoor Attacks

Despite their growing adoption across domains, large language model LLM-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific...

SoK: Data Reconstruction Attacks against Machine Learning Models: Definition, Metrics, and Benchmark

Data reconstruction attacks, which aim to recover the training dataset of a target model with limited access, have gained increasing attention in recent years. However, there is currently no consensus on a formal definition of data reconstruction attacks or appropriate evaluation metrics for...

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning

Federated learning FL allows multiple data-owners to collaboratively train machine learning models by exchanging local gradients, while keeping their private data on-device. To simultaneously enhance privacy and training efficiency, recently parameter-efficient fine-tuning PEFT of large-scale...

Trojan Horse Hunt in Time Series Forecasting for Space Operations

This competition hosted on Kaggle https://www.kaggle.com/competitions/trojan-horse-hunt-in-space is the first part of a series of follow-up competitions and hackathons related to the "Assurance for Space Domain AI Applications" project funded by the European Space Agency...

Bayesian Perspective on Memorization and Reconstruction

We introduce a new Bayesian perspective on the concept of data reconstruction, and leverage this viewpoint to propose a new security definition that, in certain settings, provably prevents reconstruction attacks. We use our paradigm to shed new light on one of the most notorious attacks in the...

An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs

Recent advances in Large Language Models LLMs have led to the widespread adoption of third-party inference services, raising critical privacy concerns. Existing methods of performing private third-party inference, such as Secure Multiparty Computation SMPC, often rely on cryptographic methods...

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...

Vulnerability of Transfer-Learned Neural Networks to Data Reconstruction Attacks in Small-Data Regime

Training data reconstruction attacks enable adversaries to recover portions of a released model's training data. We consider the attacks where a reconstructor neural network learns to invert the random mapping between training data and model weights. Prior work has shown that an informed adversar...

Nosy Layers, Noisy Fixes: Tackling DRAs in Federated Learning Systems Using Explainable AI

Federated Learning FL has emerged as a powerful paradigm for collaborative model training while keeping client data decentralized and private. However, it is vulnerable to Data Reconstruction Attacks DRA such as "LoKI" and "Robbing the Fed", where malicious models sent from the server to the clie...

Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning

Federated Unlearning FU has emerged as a critical compliance mechanism for data privacy regulations, requiring unlearned clients to provide verifiable Proof of Federated Unlearning PoFU to auditors upon data removal requests. However, we uncover a significant privacy vulnerability: when gradient...

Cutting through Privacy: a Hyperplane-Based Data Reconstruction Attack in Federated Learning

Federated Learning FL enables collaborative training of machine learning models across distributed clients without sharing raw data, ostensibly preserving data privacy. Nevertheless, recent studies have revealed critical vulnerabilities in FL, showing that a malicious central server can manipulat...

Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning

Federated learning FL enhances privacy and reduces communication cost for resource-constrained edge clients by supporting distributed model training at the edge. However, the heterogeneous nature of such devices produces diverse, non-independent, and identically distributed non-IID data, making t...

rsync: rsync server leaks arbitrary client files

A flaw was found in rsync. It could allow a server to enumerate the contents of an arbitrary file from the client's machine. This issue occurs when files are being copied from a client to a server. During this process, the rsync server will send checksums of local data to the client to compare wi...

A Numerical Gradient Inversion Attack in Variational Quantum Neural-Networks

The loss landscape of Variational Quantum Neural Networks VQNNs is characterized by local minima that grow exponentially with increasing qubits. Because of this, it is more challenging to recover information from model gradients during training compared to classical Neural Networks NNs. In this...

The remote desktop puzzle. DFIR techniques for dealing with RDP Bitmap Cache

TL;DR How RDP Bitmap Cache can reveal user activity No RDP logs? How can we reconstruct RDP activity? How cached tiles can uncover insider threats Introduction A lot of people are aware of RDP and what its functions are. It’s known for providing remote access and making life easier for...

ReCIT: Reconstructing Full Private Data from Gradient in Parameter-Efficient Fine-Tuning of Large Language Models

Parameter-efficient fine-tuning PEFT has emerged as a practical solution for adapting large language models LLMs to custom datasets with significantly reduced computational cost. When carrying out PEFT under collaborative learning scenarios e.g., federated learning, it is often required to exchan...

SoK: Timeline Based Event Reconstruction for Digital Forensics: Terminology, Methodology, and Current Challenges

Event reconstruction is a technique that examiners can use to attempt to infer past activities by analyzing digital artifacts. Despite its significance, the field suffers from fragmented research, with studies often focusing narrowly on aspects like timeline creation or tampering detection. This...

CVE-2024-52417

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in BoldThemes ReConstruction reconstruction allows Reflected XSS.This issue affects ReConstruction: from n/a through = 1.4.7...

SUSE CVE-2024-12086

A flaw was found in rsync. It could allow a server to enumerate the contents of an arbitrary file from the client's machine. This issue occurs when files are being copied from a client to a server. During this process, the rsync server will send checksums of local data to the client to compare wi...

AZL-55685 CVE-2024-12086 affecting package rsync for versions less than 3.4.1-1

A flaw was found in rsync. It could allow a server to enumerate the contents of an arbitrary file from the client's machine. This issue occurs when files are being copied from a client to a server. During this process, the rsync server will send checksums of local data to the client to compare wi...