Hierarchical Graph Neural Network for Compressed Speech Steganalysis

Steganalysis methods based on deep learning DL often struggle with computational complexity and challenges in generalizing across different datasets. Incorporating a graph neural network GNN into steganalysis schemes enables the leveraging of relational data for improved detection accuracy and...

Sparse Regression Codes for Secret Key Agreement: Achieving Strong Secrecy and Near-Optimal Rates for Gaussian Sources

Secret key agreement from correlated physical layer observations is a cornerstone of information-theoretic security. This paper proposes and rigorously analyzes a complete, constructive protocol for secret key agreement from Gaussian sources using Sparse Regression Codes SPARCs. Our protocol...

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning DL models, including recent foundation models like large language models LLMs. Users can access different compressed model versions according to their resources and budget. However, while existi...

Semi-Fragile Watermarking of Remote Sensing Images Using DWT, Vector Quantization and Automatic Tiling

A semi-fragile watermarking scheme for multiple band images is presented in this article. We propose to embed a mark into remote sensing images applying a tree-structured vector quantization approach to the pixel signatures instead of processing each band separately. The signature of the...

TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs

Chip manufacturing is a complex process, and to achieve a faster time to market, an increasing number of untrusted third-party tools and designs from around the world are being utilized. The use of these untrusted third party intellectual properties IPs and tools increases the risk of adversaries...

Side-Channel Extraction of Dataflow AI Accelerator Hardware Parameters

Dataflow neural network accelerators efficiently process AI tasks on FPGAs, with deployment simplified by ready-to-use frameworks and pre-trained models. However, this convenience makes them vulnerable to malicious actors seeking to reverse engineer valuable Intellectual Property IP through...

An Efficient Digital Watermarking Technique for Small Scale Devices

In the age of IoT and mobile platforms, ensuring that content stay authentic whilst avoiding overburdening limited hardware is a key problem. This study introduces hybrid Fast Wavelet Transform & Additive Quantization index Modulation FWT-AQIM scheme, a lightweight watermarking approach that...

Mind the Gap: a Practical Attack on GGUF Quantization

With the increasing size of frontier LLMs, post-training quantization has become the standard for memory-efficient deployment. Recent work has shown that basic rounding-based quantization schemes pose security risks, as they can be exploited to inject malicious behaviors into quantized models tha...

CVE-2022-29212

TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, certain TFLite models that were created using TFLite model converter would crash when loaded in the TFLite interpreter. The culprit is that during quantization the scale of values could b...

CVE-2022-36027

TensorFlow is an open source platform for machine learning. When converting transposed convolutions using per-channel weight quantization the converter segfaults and crashes the Python process. We have patched the issue in GitHub commit aa0b852a4588cea4d36b74feb05d93055540b450. The fix will be...

CVE-2021-37682

TensorFlow is an end-to-end open source platform for machine learning. In affected versions all TFLite operations that use quantization can be made to use unitialized values. For example. The issue stems from the fact that quantization.params is only valid if quantization.type is different that...

CVE-2021-29535

TensorFlow is an end-to-end open source platform for machine learning. An attacker can cause a heap buffer overflow in QuantizedMul by passing in invalid thresholds for the quantization. This is because the...

GenoArmory: a Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

We propose the first unified adversarial attack benchmark for Genomic Foundation Models GFMs, named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologicall...

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...

[SECURITY] Fedora 42 Update: llama-cpp-b4094-11.fc42

The main goal of llama.cpp is to run the LLaMA model using 4-bit integer quantization on a MacBook Plain C/C++ implementation without dependencies Apple silicon first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks AVX, AVX2 and AVX512 support for x86 architectures Mixed F...

[SECURITY] Fedora 41 Update: llama-cpp-b3561-1.fc41

The main goal of llama.cpp is to run the LLaMA model using 4-bit integer quantization on a MacBook Plain C/C++ implementation without dependencies Apple silicon first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks AVX, AVX2 and AVX512 support for x86 architectures Mixed F...

[SECURITY] Fedora 40 Update: llama-cpp-b3561-1.fc40

The main goal of llama.cpp is to run the LLaMA model using 4-bit integer quantization on a MacBook Plain C/C++ implementation without dependencies Apple silicon first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks AVX, AVX2 and AVX512 support for x86 architectures Mixed F...

HiColor security vulnerabilities

HiColor is a program by the individual developer D. Bohdan. It is used to convert images to 15-bit and 16-bit RGB colors. A security vulnerability exists in HiColor version 0.5.0, which stems from a heap buffer overflow vulnerability in the pngquantize function, allowing an attacker to cause a...

BIT-TENSORFLOW-2021-29537 Heap buffer overflow in `QuantizedResizeBilinear`

TensorFlow is an end-to-end open source platform for machine learning. An attacker can cause a heap buffer overflow in QuantizedResizeBilinear by passing in invalid thresholds for the quantization. This is because the...

BIT-TENSORFLOW-2022-29212 Core dump when loading TFLite models with quantization in TensorFlow

TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, certain TFLite models that were created using TFLite model converter would crash when loaded in the TFLite interpreter. The culprit is that during quantization the scale of values could b...