Astra Linux – Vulnerability found in Linux 6.1, Linux 6.12

In the Linux kernel, the following vulnerability has been resolved: perf/x86/intel: KVM: The mask PEBSENABLE must be set for the guest when the value of vCPU is used. When generating the MSRIA32PEBSENABLE value that will be loaded on the VM-Entry to a KVM guest, the value should be masked with th...

Differentially Private Relational Learning with Entity-Level Privacy Guarantees

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy DP offers a principled approach for quantifying privacy risks, with DP-SGD emerging as a standard mechanism for...

Watermarking Degrades Alignment in Language Models: Analysis and Mitigation

Watermarking techniques for large language models LLMs can significantly impact output quality, yet their effects on truthfulness, safety, and helpfulness remain critically underexamined. This paper presents a systematic analysis of how two popular watermarking approaches-Gumbel and KGW-affect...

Duality on the Thermodynamics of the Kirchhoff-Law-Johnson-Noise (KLJN) Secure Key Exchange Scheme

This study investigates a duality approach to information leak detection in the generalized Kirchhoff-Law-Johnson-Noise secure key exchange scheme proposed by Vadai, Mingesz, and Gingl VMG-KLJN. While previous work by Chamon and Kish sampled voltages at zero-current instances, this research...

Autoregressive Images Watermarking through Lexical Biasing: an Approach Resistant to Regeneration Attack

Autoregressive AR image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent misuse. However, existing in-generation watermarking techniques are primarily designed for diffusion models, where...

Hush! Protecting Secrets during Model Training: an Indistinguishability Approach

We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contained in that data via the model. The standard method for training models to avoid memorization of secret information i...

Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection

The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning CL, which updates models using a limited set of old data samples, helps preserve prior knowledge while incorporating new information. However,...

Efficient Preimage Approximation for Neural Network Certification

The growing reliance on artificial intelligence in safety- and security-critical applications demands effective neural network certification. A challenging real-world use case is certification against patch attacks'', where adversarial patches or lighting conditions obscure parts of images, for...

CVE-2020-0118

In addListener of RegionSamplingThread.cpp, there is a possible out of bounds write due to improper input validation. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is needed for exploitation.Product: AndroidVersions:...

Verifying Differentially Private Median Estimation

Differential Privacy DP is a robust privacy guarantee that is widely employed in private data analysis today, finding broad application in domains such as statistical query release and machine learning. However, DP achieves privacy by introducing noise into data or query answers, which malicious...

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries

Retrieval-Augmented Generation RAG systems enhance large language models LLMs by incorporating external knowledge bases, but they are vulnerable to privacy risks from data extraction attacks. Existing extraction methods typically rely on malicious inputs such as prompt injection or jailbreaking,...

An Efficient Private GPT Never Autoregressively Decodes

The wide deployment of the generative pre-trained transformer GPT has raised privacy concerns for both clients and servers. While cryptographic primitives can be employed for secure GPT inference to protect the privacy of both parties, they introduce considerable performance overhead.To accelerat...

MicroCrypt Assumptions with Quantum Input Sampling and Pseudodeterminism: Constructions and Separations

Whitepaper called MicroCrypt Assumptions With Quantum Input Sampling And Pseudodeterminism: Constructions And Separations...

Linux kernel 安全漏洞

Linux kernel is the kernel used by Linux, the open source operating system of the Linux Foundation in the United States. A security vulnerability exists in the Linux kernel that stems from PEBSENABLE not being masked by vCPU value in perf/x86/intel...

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...

From Trade-Off to Synergy: a Versatile Symbiotic Watermarking Framework for Large Language Models

The rise of Large Language Models LLMs has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and sampling-based. However, current schemes entail trade-offs among...

Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy

Large Language Models LLMs have gained significant popularity due to their remarkable capabilities in text understanding and generation. However, despite their widespread deployment in inference services such as ChatGPT, concerns about the potential leakage of sensitive user data have arisen...

Enhancing IoT Cyber Attack Detection in the Presence of Highly Imbalanced Data

Due to the rapid growth in the number of Internet of Things IoT networks, the cyber risk has increased exponentially, and therefore, we have to develop effective IDS that can work well with highly imbalanced datasets. A high rate of missed threats can be the result, as traditional machine learnin...

DNS Query Forgery: a Client-Side Defense against Mobile App Traffic Profiling

Mobile applications continuously generate DNS queries that can reveal sensitive user behavioral patterns even when communications are encrypted. This paper presents a privacy enhancement framework based on query forgery to protect users against profiling attempts that leverage these background...

Energy-Efficient NTT Sampler for Kyber Benchmarked on FPGA

Kyber is a lattice-based key encapsulation mechanism selected for standardization by the NIST Post-Quantum Cryptography PQC project. A critical component of Kyber's key generation process is the sampling of matrix elements from a uniform distribution over the ring Rq . This step is one of the mos...